Hi, one of the authors here, this is awesome, thanks so much for doing this! Is it ok if we link this on the Github page?
@thenerfguru
Жыл бұрын
Absolutely!
@thenerfguru
Жыл бұрын
Thanks for creating the project! I love where the technology is headed.
@thebigpicture1052
Жыл бұрын
Hello author. Please make it export to unreal engine or blender with modelling data from cheap lidar or generated from 2d to 3D ai. Lot of indie filmmaker always want to do vfx. This skip a lot of things which only studio with millions of dollar could do afford to do. if a decent pc cn render whats on a virutal camera frame after importing it in unreal engine n it would revamp entire market n small player... Thank you in advance ❤.
@crossybreed
Жыл бұрын
Hello author, One beginner question. Why only cuda based ? Will it run on Ryzen 5 5800G and above using APU as VRAM ? As this guy showed how to run AI models on CPU! He showed Cuda based AI running on CPU and that results are almost equals to RTX 4080! Is it possible? kzitem.info/news/bejne/qW-lx4KQh3yVpawsi=A0FjUtKPOUaERFJ2
@skinkie
Жыл бұрын
@@crossybreedtypically the answer is, that the software development for cuda has been more mature for a longer time. That does not mean that cuda is 'stable' especially since its support typically requires recent hardware. And where cuda supported older hardware, more recent development does not support those cuda versions. In that respect AMD has done crazy things theirselves for example with (or not anymore) supporting OpenCL. And only recently HIP starts to appear, which (obviously) requires porting existing CUDA and OpenCL code. It is only very recently that you see academic work on github, before the code you saw in papers was never released. I don't think it is in the researchers best interest to make the most portable code, but in essence just prove that an idea works.
@Raketenclub
Жыл бұрын
man i remember we learned the theory in the 90s... movement detection due to motion blur and calculate / recreate vectors and depths in a blackn white photo... but the computerpower was so limited we were not really able to proceed......... working on paper, lol, later volumetric clouds came in and now we have this.....this is truely awesome..... something i had dreamed of for decades, recreated my own 3d scenes for months, now its only a video and photos you put in an ai. i am totally flashed.
@thenerfguru
Жыл бұрын
In theory, this definitely wasn’t new! Now we have the compute hardware, we live in an amazing time.
@dested1
Жыл бұрын
IT worked first try, this is incredible. I have a 3d cloud model of my living room forever. Great tutorial, super detailed.
@thenerfguru
Жыл бұрын
So awesome to hear that! People usually struggle to capture rooms.
@karineavetisyan7767
11 ай бұрын
Hey I've trained the model using Gaussian splatting. I can see the result in nerfstudio and render video. But how to get .ply or .obj file of mesh so I can see my result with colours with any 3d viewer. Please, help me if you have found a solution for this.
@OlliHuttunen78
Жыл бұрын
Hey this is very cool! Thank you a lot. I finally managed to generate my first Gaussian Splatting model with your instructions. Lot of steps in here but it finally works! Nice that you have made windows version to github from the original. Thank you! This is so intresting!
@thenerfguru
Жыл бұрын
Thanks for the comment! Have fun with it!
@karineavetisyan7767
11 ай бұрын
I've trained the model using Gaussian splatting. I can see the result in nerfstudio and render video. But how to get .ply or .obj file of mesh so I can see my result with colours with any 3d viewer.
@patrickcasella
Жыл бұрын
been seeing this everywhere, but nobody wanted to show how to do it! Thank you so much for this. I'm on my way to make some really awesome art. Keep it up!!
@thenerfguru
Жыл бұрын
Godspeed! If you post anything on social, tag me and I’ll reshare it. I’m fairly active on LI and X
@sirens3237
7 ай бұрын
I cannot thank you enough for this. I went from knowing basically nothing to a completed scene in 3 hours. It would have been much faster but I had the wrong CUDA version. You absolutely nailed this tutorial!
@thenerfguru
7 ай бұрын
Thank you!
@marcosmoura911
4 ай бұрын
Which version did you have and which you did you need ?
@artiexus
3 ай бұрын
Thank you very much for making this video! You're a great teacher, I had no problems following this and I'm very happy with how my first splat turned out.
@dialectricStudios
Жыл бұрын
the coolest advancement in neural rendering! amazing stuff man
@thenerfguru
Жыл бұрын
I agree! It is so amazing because it renders in real-time and looks crazy detailed.
@dialectricStudios
Жыл бұрын
@@thenerfguru the first game engine to utilize this technology will make billions. Gaben take notes
@w000w00t
Жыл бұрын
This video is great! Thank you for being so generous with your knowledge about this cutting edge technology! ...and the command prompt tips were GOLD! :)
@thenerfguru
Жыл бұрын
Thank you! I usually find the biggest hurdle for people to get into this tech is understanding command prompt. I find it funny that I struggle with Unreal Engine blueprints which is arguably easier because it's visual.
@karineavetisyan7767
11 ай бұрын
I've trained the model using Gaussian splatting. I can see the result in nerfstudio and render video. But how to get .ply or .obj file of mesh so I can see my result with colours with any 3d viewer.
@markinmkn
11 ай бұрын
After 3 days trying I get!! I just want to say thank you for your tutorial!! I have some troubles and after solving that the results is really amazing!!
@pseudopod77
4 ай бұрын
you nailed it! thank you. had been led astray on other tuts and this one was very straight forward. I should drive all the confused viewers from other tuts this way.
@dougdaniels7848
10 ай бұрын
Man I don't even know where to start... I've been struggling with the submodules diff-gaussian-rasterization and simple-knn and have been combing through the GitHub comments about the same issue for hours... nothing seems to work. Do I just need to uninstall all components and start fresh? Seems to be a lot of confusion about which CUDA version to use and how to install torch.
@tokyowarfare6729
Жыл бұрын
I've a 3090 TI, I feel blessed that I'll be able to mess with this tech. Tx a lot for hte tutorial.
@thenerfguru
Жыл бұрын
You’re welcome!
11 ай бұрын
I was getting errors with "diff-gaussian-rasterization" and "simple-knn" when running the command "conda env create --file environment.yml". I just wanted to let others with the same problem know what I did to solve it. I had to add "C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\bin\Hostx64\x64" to PATH in order for the build command to find cl.exe. And since the "conda env create" command was aborted before it was finished I had to start a new CMD window after adding to PATH and rerun the commands, ending with "conda activate gaussian_splatting" and from there I typed "conda env update --file environment.yml" to start the build process again. Hope it helps someone. 😊
@lilmanpurse8603
11 ай бұрын
I had the same issue and this tip didnt work, i got the exact same errors again. I have tried everything i could find to address the issues i am getting but it seems like im at a dead end here. Hope someone can make a more accessible version soon
@herrdrfink1020
11 ай бұрын
Make sure to run this commands with Administrator rights after adding the path.@@lilmanpurse8603 activate pip install -e submodules/diff-gaussian-rasterization pip install -e submodules/simple-knn
11 ай бұрын
@@lilmanpurse8603scroll down to the bottom of the git and check the common issues section. I saw that a more complete step by step instruction was there last time I checked. It might be a small step missed. Like not closing your command window in between changes to the PATH for instance. Hope you find a solution.
@user-vt9qk9xc2k
5 ай бұрын
@@lilmanpurse8603 i have tried two ways to solve that, one is the adding of the VS path just this bro said above, and i tried to change the vision of my cudatoolkit into 11.8 from 12.3. I dont know which of these worked, but i solve it now. Very necessary to remind is that, after you make some changes in environment, restarting the computer may be very effective.😂😂
@Bantammenace1903
Жыл бұрын
Bravo. I will give this a go with images captured with my Leica BLK3D and compare the result with the coloured textured mesh created from the same images in RealityCapture.
@thenerfguru
Жыл бұрын
Share the results! Completely different outputs and visualization techniques.
@rubyspot
Жыл бұрын
I would love to see it. Do you have LinkedIN or something?
@esuelle
11 ай бұрын
I managed to get pretty cool results on a RTX2070S with just 5000 iterations. The training step was pretty fast too, under 10 minutes! Incredible technology. I can only imagine how much more incredible it's going to get in a couple of years. Thanks for the video, everything was explained very clearly.
@thenerfguru
11 ай бұрын
Glad it worked well for you! I bet you could run it all to at least 7000 iters as well.
@karineavetisyan7767
11 ай бұрын
I've trained the model using Gaussian splatting. I can see the result in nerfstudio and render video. But how to get .ply or .obj file of mesh so I can see my result with colours with any 3d viewer.
@JOMFRUHOLMEN
10 ай бұрын
This is going to change the world.
@JankyzFSX
11 ай бұрын
Amazing job guys! As a surveyor i know photogrammetry and this is another level ♥
@thenerfguru
11 ай бұрын
🙌
@VaunaKiller
Жыл бұрын
Imagine capturing images for google street view using this technique 😃 I won't leave home ever again
@BOLL7708
Жыл бұрын
I don't have the machine for this, but I immediately want to see what one of these splatted scenes look like in a VR headset. 😁
@thenerfguru
Жыл бұрын
Keep an eye out for VR enabled 3D Gaussian Splats. Plus, it takes a lot less GPU power to view these. Training is the VRAM bottleneck
@olgaforce6678
Жыл бұрын
I just ran it with a 3070 GPU with 8GB
@andershjemdahl6547
Жыл бұрын
@@thenerfguruI can’t wait! What res do you expect to be able to pull off, say on a Quest 2 using Steam vs HMD only?
@TomasDelBianco
Жыл бұрын
@@olgaforce6678 Did you manage to train a model with a 3070?
Жыл бұрын
@@olgaforce6678how did it go?
@gridvid
11 ай бұрын
Correct me if I'm wrong, but it should be possible to convert any 3D blender scene into Gaussians because we already know the position of the virtual camera from the rendered 3D scene. So it should be possible to create photorealistic, interactive scenes pretty fast from 3D scenes created in blender from a few rendered images using cycles. This could be a revolution in gaming as well.
@mattizzle81
11 ай бұрын
Indeed you could render some pretty computationally expensive scenes and convert it to this format.
@Alex29196
11 ай бұрын
@@mattizzle81 I converted a 3D blender scene into Gaussians, and looks amazing. You can make movie production with a low en pc if you render de scene in eevee.
@robertmayster7863
9 ай бұрын
Not really convinced that a triangle based, photorealistic blender scene renders faster or better if you convert it to gaussians. It's just a different, more complex way to represent the same dataset. I would argue you actually lose performance and quality since you approximate the original geometry and shaders with particles and 4th order spherical harmonics.
@zyang056
8 ай бұрын
Use cycles for offline rendering. GS for realtime rendering with the lights and transparency baked in.@@robertmayster7863
@BjarneKort
Жыл бұрын
Been looking forward to this, thank you!
@thenerfguru
Жыл бұрын
You're welcome!
@russkiy225
Ай бұрын
@@thenerfguru i think this wont work on my 12 year mid-end laptop im currently on it. 4g ram processor is b960 intel pentium gpu is amd radeon 7400M series or amd radeon 7400G dual. its windows 7 and also i optimized it as much as i can im using it already 9 years and it runs all perfectly IDK i just want to noclip through mp4 videos
@ZergRadio
11 ай бұрын
Nice tutorial. I would like to give a suggestion. When showing webpage's or application it would be great if one could zoom in, so the text is bigger, so people with problematic sight could see what is on screen :) Thanks
@thenerfguru
11 ай бұрын
Great suggestion!
@ADUuniverse
11 ай бұрын
\gaussian_renderer\__init__.py", line 14, in from diff_gaussian_rasterization import GaussianRasterizationSettings, GaussianRasterizer ModuleNotFoundError: No module named 'diff_gaussian_rasterization' It showing me this error! tried to solve it but it isn't working... PLS help!
@Peluche070
11 ай бұрын
we used to use this 13 years ago for 2D--3D streo conversion with polar axis. :) Now its realtime hardware based. It used to be software based on depth maps layed out manually. :) now the hardware auto creates depth maps that changes it.
@mars8164
6 ай бұрын
Very detailed instructional video, love from new beginner. :)
@kurtnana9927
8 ай бұрын
Very Helpful Guide. Thank you so much for making this video and saving a lot of time for others trying to understand and install the program :D
@thenerfguru
8 ай бұрын
Glad it helped!
@Daexx5
Ай бұрын
I was here before it went mainstream. It's awesome.
@Thats_Cool_Jack
Жыл бұрын
It feels like just yesterday when I tried out Nvidia nerfs and was disappointed by it's limited use but now here we are with visuals rendering out in real time smoothly :o
@Thats_Cool_Jack
Жыл бұрын
wow thats a lot of vram XD
@thenerfguru
11 ай бұрын
@@Thats_Cool_Jack The requirement is dropping fast.
@MatthewRumble
11 ай бұрын
I am having the error on the command prompt of "conda is not recognized as an internal or external command". I'm stuck at 16:30. I installed anaconda and restarted my computer but it didn't work
@thenerfguru
11 ай бұрын
Without seeing the exact error code, I can’t for sure know what is happening. See if this solves your issue: github.com/graphdeco-inria/gaussian-splatting/issues/146
@user-nb2tf1ee6u
Ай бұрын
During the process of using gaussian-splatting-Windows, when the image files originally in the 'input' folder are processed by python convert.py -s and output to the 'images' directory, they reduce in number from dozens to just a few, and these images now display a wide-angle effect. What could be the issue, and how should one go about troubleshooting this?
@tjjtan8461
7 ай бұрын
Really COOOOL video! Thanks for the guide and I successfully made my own 3D model!
@ananpinya835
Жыл бұрын
Wow amazing, this is great work! I am looking forward of applying this technology on google map's street view.
@thenerfguru
Жыл бұрын
I'm sure this technology or similar will be integrated into their new Immersive View.
@Musetrigger
11 ай бұрын
Well, I ran the optimizer, and I got a problem. Encountered error while trying to install package. -> simple-knn Further up it reads, ERROR: failed building wheel for simple-knn. Very peculiar. Not sure where to go from here.
@thenerfguru
11 ай бұрын
Without seeing the whole error, it's hard to know exactly the problem. This has fixed most people's issue around building the project: github.com/graphdeco-inria/gaussian-splatting/issues/146
@Musetrigger
11 ай бұрын
@@thenerfguru I managed to snoop around for a solution. Thank you for replying! I haven't tried anything yet but I'll know where to go if things go wrong.
@renderinmymind
11 ай бұрын
soo good man running perfectly. Thanks for the video
@thenerfguru
11 ай бұрын
You're welcome!
@SGRuLeZ_Art
11 ай бұрын
Thank you, Jonathan! It works and it causes a storm of emotions in me. Just crazy!)
@tuntutilmu6700
4 ай бұрын
Can you show how to do this in ubuntu? I have spent few days doing this in my ubuntu 22.04😢
@user-iq8kw8zb3v
8 ай бұрын
Hello, I have encountered some minor trouble. Could you please advise me on how to resolve this issue when I display "colmap is not an internal or external command, nor is it a runnable program or command" while running the program. Excuse me for bothering you
@thenerfguru
8 ай бұрын
You need to install COLMAP and add it to path. I cover how to do that in this video at the 21 minute mark: kzitem.info/news/bejne/rZ53x2V4cnV3mI4si=RhOj9xDjuhbzmUYv
@user-iq8kw8zb3v
8 ай бұрын
Thank you very much.
@RealityCheckVR
Жыл бұрын
Hey there! I'm having trouble getting the SIBR viewer to work properly as it always closes soon after I submit the command. I am using an nvidia 1080ti gpu, still, it tells me "Sorry, need at least compute capability 7.0+!" (I believe my GPU is 6.1). I tried to install NERFSTUDIO but after hours and hours of attempts, I got stuck during the install part when tinycudann would refuse to build the wheel. I can get Instant NGP working to train and view NERFS but right now I have no ability to view my Gaussian Splats. It seems like I can train Gaussian Splats but not view them. Does anybody have any ideas?
@hui7684
Жыл бұрын
I have same case as yours: the viewer windown is white and closed fast, NVIDIA 1080Ti, Sorry, need at least compute capability 7.0+!. Could anyone can help to solve this problem? Many thanks for the great paper and viedeo. Thanks in advance!
@thenerfguru
Жыл бұрын
What version of CUDA toolkit do you have installed?
@RealityCheckVR
Жыл бұрын
Hey Nerf! Thanks for the video) I'm running CUDA 11.8 (more specifically: Cuda compilation tools, release 11.8, V11.8.89 Build cuda_11.8.r11.8/compiler.31833905_0) @@thenerfguru
@RealityCheckVR
Жыл бұрын
I've tried to install Nerfstudio but when I try to start the viewer I get this error "ModuleNotFoundError: No module named 'nerfstudio.scripts.gaussian_splatting'"@@thenerfguru
@mdp7193
Жыл бұрын
@@thenerfguru @RealityCheckVR I'm having the same issue as well and I installed the 11.8 version of the CUDA Toolkit
@360_SA
Жыл бұрын
Great video amazing tutorial skills. I would like to know if I can use 360 photos or does it have different setting
@thenerfguru
Жыл бұрын
You can’t natively use 360 video. It needs to be separated into parts. I’ll make a tutorial soon.
@therealkhroma
Жыл бұрын
Much thanks. Will be trying this out tomorrow.
@thenerfguru
Жыл бұрын
Great! Let me know how it goes!
@klexyuming3144
11 ай бұрын
During the 'conda env create --file environment.yml' step, i have this error appearing.. "Pip subprocess error: ERROR: Directory 'submodules/diff-gaussian-rasterization' is not installable. Neither 'setup.py' nor 'pyproject.toml' found. failed CondaEnvException: Pip failed' Can anyone advise me on what to do?
@thenerfguru
11 ай бұрын
Does this solve your issue? github.com/graphdeco-inria/gaussian-splatting/issues/146
@PeeosLock
11 ай бұрын
yes, this solve my error related "diff_gaussian_rasterization" (1) reinstall VIsual Studio 2022, install more in modify (2) run ananconda : conda activate gaussian_splatting cd /gaussian-splatting pip install submodules\diff-gaussian-rasterization pip install submodules\simple-knn thank you @@thenerfguru
@alangrant3415
Жыл бұрын
Does it matter that if has cudatoolkit 11.6 in the dependencies list of your environment.yml? I'm still having trouble installing Optimiser Pip dependecies always fail, nothing on Git yet to help solve
@thenerfguru
Жыл бұрын
What does the failure say? Have you tried asking for help on the main GitHub project?
@thenerfguru
Жыл бұрын
I also did see that. If you have 11.8, you should already be satisfying the requirement and it will skip it.
@yanmeiwang-km4ko
5 ай бұрын
Thank you very much for the video, it helped me a lot. Thank you for your generous sharing!
@guineafowllab
Жыл бұрын
Thank you so much, this is amazing! I'm having trouble with the training process. The error message says "ModuleNotFoundError: No module named 'diff_gaussian_rasterization'." What should I do?
@guineafowllab
Жыл бұрын
And I actually see it here: gaussian-splatting\submodules\diff-gaussian-rasterization 😶🌫
@thenerfguru
Жыл бұрын
Did you resolve it? This may be a good question to ask in the main GitHub repo.
@BirdChen
Жыл бұрын
I also have an issue with incomplete installation, which has been bothering me for several days. The settings of my system are the same as the ones shown in the video. Please keep me informed if there's any progress.
@olgaforce6678
Жыл бұрын
I'm stuck at same error.
@thenerfguru
Жыл бұрын
Have any of you saved the logs of what happened? The install of diff-Gaussian-rasterization failed…and probably Simple-knn. If I saw the compilation code, I could help.
@DGFig
Жыл бұрын
Amazing tutorial. I've been looking forward to this. Unfortunately, the 24 GB VRAM requirement will keep me out of the game for a couple of years, or until the memory requirements are reduced. Anyway, thanks a lot!
@thenerfguru
Жыл бұрын
What’s your current GPU?
@DGFig
Жыл бұрын
It's currently an RTX 2060 with laughable 6 GB of VRAM. I'm buying a 4070 with 12 GB soon, but that will still be only half of the suggested minimum. Just for the experience, I started training a 120-image dataset (downscaled to FullHD resolution) and, to my surprise, I got no immediate out-of-memory errors. It started training relatively fast, but soon speed dropped to about 1 it/s. It's still training, but just too slow to be feasible.@@thenerfguru
@DGFig
Жыл бұрын
So, I've decided to let it run for as long as it needs. It's at about 5k iterations now, going at about 3 it/s. I'll let you know if it manages to go all the way.
@DGFig
Жыл бұрын
Final update: after many hours, training speed dropped to 0.1 it/s (10 s/it), which made me pull the plug. I got as far as 5600 iterations. I'll try again when I get the 12 GB 4070.
@thenerfguru
Жыл бұрын
@@DGFig Hmmm. I am sorry to hear about that! Did you change any of the processing parameters or just saw how far it would go? Someone is working on a super fast training version of this that still needs more VRAM, however, you can modify the training variables to use less.
@cosmicfissure924
10 ай бұрын
Thank you for sharing this valuable tutorial! It was extremely informative and gave me a much stronger understanding of 3D Gaussian Splatting. However, while following the instructions carefully, I encountered a minor roadblock when trying to execute the command: python train.py -s Unfortunately, I came across the following error: Traceback (most recent call last): File "train.py", line 16, in from gaussian_renderer import render, network_gui File "C:\Users\wamr1\Documents\Proyectos\InstNerf\gaussian-splatting\gaussian_renderer\__init__.py", line 14, in from diff_gaussian_rasterization import GaussianRasterizationSettings, GaussianRasterizer ModuleNotFoundError: No module named 'diff_gaussian_rasterization' It seems there's an issue with the 'diff_gaussian_rasterization' module. Do you have any suggestions on how to resolve this issue? I greatly appreciate any further guidance you can provide!
@Dima8D
10 ай бұрын
Same thing, have you find the solution?
@shindeta
9 ай бұрын
same problem here...
@cosmicfissure924
9 ай бұрын
@@Dima8D To address the error mentioned: Open your terminal and navigate to the location of the 'diff_gaussian_rasterization' module. Use the cd command to change to the correct directory. Once there, run python setup.py install and press Enter. This will install the necessary module. Repeat these steps for the 'simple-knn' folder.
@Anttisinstrumentals
11 ай бұрын
As someone who has struggled with the installation, the magick lies in cuda 11.7 . it does not work with 11.6. it does not work with 11.8. but with 11.7 perfect. Everything installed fine.
@patrickjdarrow
8 ай бұрын
I was able to do everything with 11.8, with the exception of the conversion which required I turn off gpu. Your fix seems cleaner though
@marcosmoura911
4 ай бұрын
@@patrickjdarrow Why did u have to turn off the gpu and how you found that out
@prateeksrivastava9123
9 сағат бұрын
Building wheel for diff_gaussian_rasterization (setup.py): finished with status 'error' --> Always this error is coming while running the --> conda env create --file environment.yml
@carlosreynoso8303
11 ай бұрын
Great tutorial. Thanks!
@thenerfguru
11 ай бұрын
Thank you!
@attentiondeficitdisorder
11 ай бұрын
Thank you for the tutorial. Very helpful.
@yourSPON
11 ай бұрын
when I enter this command "ffmpeg -i {path to video} -qscale:v 1 -qmin 1 -vf fps={frame extraction rate} %04d.jpg" it tells me "permission denied"
@landeros666
7 ай бұрын
I have the same problem, did you find any solution? Thanks
@luke_foxy5170
8 ай бұрын
you need to set up the enviornment inside the anaconda prompt. cmd didn't work for me
@thenerfguru
8 ай бұрын
I ran into this one on machine, but not my other. I don’t know why 🤷♂️
@jchretien45
11 ай бұрын
Hey man, I'm stuck on the very last step. I did the training and everything says it was a success, but when I try to run the viewer I get could not find config file 'cfg_args'. But its clearly in the output folder
@thenerfguru
11 ай бұрын
That is super odd. Personally, I am not a fan of the viewer. I suggest using Nerfstudio or Unity for viewing. I made videos on both: Nerfstudio: kzitem.info/news/bejne/omd9yK2Zo2KTiqwsi=ZEZLnnJTkXrSn52I Unity: kzitem.info/news/bejne/lpV9x4SPe3qigqQsi=dremDVE1h9L3KgD0
@arqrenderz6210
11 ай бұрын
Getting the same error here..
@jonatan01i
Жыл бұрын
Thank you very much for making this more accessible!
@thenerfguru
Жыл бұрын
You're very welcome!
@user-iq8kw8zb3v
8 ай бұрын
Hello, may I ask if in the final step "SIBR_gaussianViewer.appexe - m", my computer only has one window with no content, and then it disappears. It appears in the command window [SIBR] -- INFOS --: initialization of GLFW "[SIBR] -- INFOS --: OpenGL Version: 4.6.0 NVIDIA 531.14 [major: 4, minor: 6]" How should this be resolved?
@scottcedarleaf6243
11 ай бұрын
Hi Jonathan, I'm having trouble at the Installing the Optimizer. When entering the conda env create --file environmnet.yml in cmd. I get the following error 'conda' is not recognized as an internal or external command, operable program or batch file. Any ideas?
@thenerfguru
11 ай бұрын
Either conda is not installed, or it's not added to PATH. Did you install Anaconda or Miniconda already?
@scottcedarleaf
11 ай бұрын
Hi Jonathan, thanks for the reply. It worked after installing miniconda.
@yuxiangwang9624
4 ай бұрын
I have a really naive question: I thought 3DGS would need the pose from the camera in addition to the pictures. How did you get around that by simply taking a video?
@lluismh
11 ай бұрын
Hi Jonathan!! that's awesome. thanks for your video. I followed carefully the whole process, but when i'm going to create the conda env, with the line: conda env create --file environment.yml i can't go on, cause i have an error message. I have the result of the process in cmd in a text file (if you need) , but in brief, i get something like this: Processing e: erf\gaussian-splatting\submodules\diff-gaussian-rasterization Preparing metadata (setup.py): started Preparing metadata (setup.py): finished with status 'done' Processing e: erf\gaussian-splatting\submodules\simple-knn Preparing metadata (setup.py): started Preparing metadata (setup.py): finished with status 'done' Building wheels for collected packages: diff-gaussian-rasterization, simple-knn Building wheel for diff-gaussian-rasterization (setup.py): started Building wheel for diff-gaussian-rasterization (setup.py): finished with status 'error' Running setup.py clean for diff-gaussian-rasterization Building wheel for simple-knn (setup.py): started Building wheel for simple-knn (setup.py): finished with status 'error' Running setup.py clean for simple-knn Failed to build diff-gaussian-rasterization simple-knn Installing collected packages: simple-knn, diff-gaussian-rasterization Running setup.py install for simple-knn: started Running setup.py install for simple-knn: finished with status 'error' I don't know wwhere the problem could coming, and don't know if you can help me a little with this. Anyway, thanks for your time and for the awesome video.
@jakubkucera2806
11 ай бұрын
same problem here unfortunately
@TudorIrimescu
10 ай бұрын
You need Microsoft Visual C++ 14.0 or greater installed to compile the modules. Ran into the same issue. Install that, restart the computer, delete the conda environment and try again from scratch.
@Woojtyla
10 ай бұрын
Ur the best! thanks for this tutorial mate❤❤❤
@qbaismo728
11 ай бұрын
dankeschön. thank you for doind this, it was a very good explanation
@Atlas_Redux
10 ай бұрын
I am happier and happier every day for getting an RTX 4090...
@thenerfguru
10 ай бұрын
Haha! Yes!
@Atlas_Redux
10 ай бұрын
@@thenerfguruHave you had any luck opening it in Blender or Maya? I'm getting no textures, no matter what. I can open Meshroom solutions just fine in Blender, but that is of course a different worse method. I bought the plugin for Unreal Engine though, and that works like a charm.
@vjcatalyst7830
11 ай бұрын
Awesome video! Have you seen the paper for Dynamic 3d gaussian splatting? Code is suppost to come out soon. It looks very exciting.
@thenerfguru
11 ай бұрын
I have seen it! The only downside is that requires over a dozen cameras in an array recording simultaneously.
@SolidClouds_NL
11 ай бұрын
Awsome Video! We are getting this message while training the model: Tensorboard not available: not logging progress [30/09 12:35:06] Reading camera 990/990 [30/09 12:35:15] Loading Training Cameras [30/09 12:35:15] [ INFO ] Encountered quite large input images (>1.6K pixels width), rescaling to 1.6K. If this is not desired, please explicitly specify '--resolution/-r' as 1 [30/09 12:35:15] . other then that it seems like it is busy because it not allowing me to add a new cmd. Do you know how to resolve this?
@mn04147
2 ай бұрын
wow you are so kind this video is so easy to understand tank you
@EconaelGaming
Жыл бұрын
Any way to set the size of the render target of the viewer? The resolution of the rendered image is kinda small. I'd like to try 4k. EDIT: --rendering-size 3840 2160 getting cinematic 24fps on a 1660Ti !!
@thenerfguru
Жыл бұрын
So that sizes the viewer. My hunch is that when you trained the data, the images were downscaled to 1.6k. That's fine though, you get awesome results still.
@LTE18
Жыл бұрын
Thanks for the video and managed to get it working. As someone who is new to this radiance field rendering.. may I ask is there a way to use this data and convert it into a 3d object? Like 3d scanning? What uses/application can I use this data for besides viewing it with a viewer? Thanks
@thenerfguru
11 ай бұрын
If your goal is 3D modeling and not novel view synthesis, I suggest some other method such as Neuralangelo. Meshes was not the intended goal of this project.
@AzadBalabanian
Жыл бұрын
Very useful tutorial. Thanks mate
@thenerfguru
Жыл бұрын
Glad you found it useful! More coming later this week.
@TRVRBR
10 ай бұрын
Hi! Great project! How about adding support for EXR?))) It would be a fantastic opportunity to create HDR projects, such as those for cinema, for example. I just filming a low-budget historical movie, and I really appreciate your software!
@EventHorizonVR2023
Жыл бұрын
What 360 Camera did you use for this Splat and which one do you recommend> I have the Insta360 RS One Inch and the Ricoh Theta X.
@thenerfguru
Жыл бұрын
Those would work great. I have the RS One Inch
@manu.vision
Жыл бұрын
Well done!!
@thenerfguru
Жыл бұрын
Thank you!!!
@blynch1751
10 ай бұрын
Awesome video! Any suggestions where you can get high quality drone footage like this (following a similar orbit path)? I'm performing research around various NeRF / gsplat models
@pedrodias8186
11 ай бұрын
Hi. At first very thankful for your tutorial. But there are some failures showed up in my computer. "Pip subprocess output: Pip subprocess error: ERROR: Directory 'submodules/diff-gaussian-rasterization' is not installable. Neither 'setup.py' nor 'pyproject.toml' found. WARNING: There was an error checking the latest version of pip. failed CondaEnvException: Pip failed" plz help me.
@timtraber3120
11 ай бұрын
Same problem
@thenerfguru
11 ай бұрын
Without seeing the whole error, it's hard to know exactly the problem. The project was not built successfully. This has fixed most people's issue: github.com/graphdeco-inria/gaussian-splatting/issues/146
@BlenderBob
10 ай бұрын
Cool video! I have been able to load some of the demos in the viewer so that part works. What doesn't is when I try the python train script. I get this error: ModuleNotFoundError: No module named 'diff_gaussian_rasterization' Any idea?
@zerosaturn416
10 ай бұрын
same i’ve been looking all over the internet for a solution but could find one.
@BlenderBob
10 ай бұрын
@@zerosaturn416 run these: pip install ./submodules/diff-gaussian-rasterization then pip install ./submodules/simple-knn
@thenerfguru
10 ай бұрын
The code failed to build properly when installing everything. I suggest checking out this troubleshooting thread: github.com/graphdeco-inria/gaussian-splatting/issues/146
@Trendish_channel
6 ай бұрын
Hi! Thanks! If I have 2 iphones filming static videos from different angles is it possible to combine the fuutages to create 1 scene with better quality? What about movement? Is it possible to animate gaussian splatting scene?
@davideghirelli4453
11 ай бұрын
is it possible to export the data to other app like c4d or 3ds??
@thenerfguru
11 ай бұрын
Not currently with this project.
@belzebubukas
10 ай бұрын
@thenerfguru hi, I have an idea that would utilise differentiable gaussian splatting, and I have a couple of questions you might be able to answer - would save me tons of time trying to figure it out myself. 1) Is orthographic camera available, in addition to perspective camera? 2) Currently the splats disappear when they are close to the camera (which makes sense for your use case). Would it be possible to disable this? If both are true, it would be possible to "slice" through a set of splats, which might have interesting use cases. Vertex representation provided by pytorch3d is unfortunately unsuitable for my purposes...
@StevePaulSounds
10 ай бұрын
I'm on a 2080 Ti - Whenever I try to keyframe in the viewer I can't move the camera anymore. Is there something wrong with the software, my graphics, or am I doing something wrong? How's it supposed to work?
@user-gx7un8uu7h
8 ай бұрын
Awesome Tutorial!
@thenerfguru
8 ай бұрын
Thank you!
@GreenTea-101
11 ай бұрын
Jonathan, thanks for doing this. As the data is effectively pointcloud based, can a wireframe mesh be made from the source data along the lines of poisson or similar methodology? Also, what lighting data do we get from the result-- can this environment be used to calculate a 3D radiance (if not raytrace) model? Very exciting stuff-- apologies if you've gone into detail on this elsewhere.
@thenerfguru
11 ай бұрын
Great questions. You could always run the imagery in a photogrammetry suite to get a mesh, also, something like SDFStudio would be a great option. All of the lighting is baked in. No one has really addressed the issue yet.
@GreenTea-101
11 ай бұрын
@@thenerfguru hrmmm.. you could, but if the GASP has already created a point cloud, it lives within a coordinate system so getting a 1:1 parity would be ideal.
@lodewijkluijt5793
11 ай бұрын
Are there limits to the size of the dataset? I have experiences NeRFs falling apart after beeing fed too many images. Have you heard of or experienced any limits of GS yourself?
@thenerfguru
11 ай бұрын
You are going to run into limits on VRAM when training the data. I think more photos are fine, it just depends on what those photos are.
@pierrecharpentier6730
11 ай бұрын
How would one go about cleaning up the point cloud (PLY) files manually in order to reduce their size or the some noise around critical objects in the scene for example? Blender seems to be able to open them fine, but I'm worried there might be some vertex color information or other type of metadata that it deletes when importing or re-exporting them.
@asherguild
11 ай бұрын
CloudCompare
@pierrecharpentier6730
11 ай бұрын
@@asherguild have you tried it? does it retain every bit of info for each vertex from the original file when you export/save it again?
@thenerfguru
11 ай бұрын
CloudCompare wouldn’t be an easy solution. You would have to save all of the data associated with each point. That’s not something it does by default.
@bigsmokegames9493
11 ай бұрын
@@thenerfguru True for post processing, but I was thinking of preprocessing
@liquidmasl
Жыл бұрын
So, i have a high density laser scanned pointcloud, and i have 360 pano images every few meters, it should be possible to use that directly right? my pointcloud is super high density and the points have color already, but for training it will still need the panos i suppose? damn i want to get this to work
@thenerfguru
11 ай бұрын
Still need the panos if you were to hack it. You would also need camera poses. The sparse point cloud is just an initial set of locations for splats to be located at. From there, the training will move and morph the splats to fit the scene.
@VaunaKiller
Жыл бұрын
Can we use this as an alternative to Nerf (or in combination with) to convert video/images into "nicer" 3d models, addressing downsides of nerfs (garbled geometry, muddy "textures")? Certain angles certainly look better compared to nerfs output (even stunning so), but I don't quite understand if these "gaussian points" can enable geometry estimation or provide better point colorss? "Dumb" way that comes to my mind is to produce video/lots of pictures straight from 3d gausiann viewer (hoping to get the perfectly consistent stabilisation/angles/image quality compared to original video) and feed them into Nerfstudio, but I am sure this is not an optimal approach 😅
@AIWarper
10 ай бұрын
Is there a downside to allowing it to autoscale my images? I have my drone imagery in 4k resolution but it wants to default to 1600 width instead of 2160 (I know I can set r1) Basically I am asking should I force native resolution or is it a waste
@thenerfguru
10 ай бұрын
In my tests, it’s usually just a waste. However, you can try r 2: half scale. That may be a bump from 1600z
@TheLorsange
9 ай бұрын
Hi, Great tutorial, thanks a lot!!! Is there any explanation how to implement CUDA12? Didn't find it in repo
@reliquary1267
11 ай бұрын
Can I use a RTX 3080 10GB with 32GB of shared memory or will that not work yet?
@thenerfguru
11 ай бұрын
You can easily get away with 7000 iterations, probably even 10k. Downsampling images to 1.6k and not using too many will help too.
@user-xn7ol1gh6c
8 ай бұрын
Dear author, hello. Regarding your Gaussian pasting, I would like to ask, actually, I want to use it to export 3D models. Yes, I see that the generated effect is very realistic, and I want to export the characters or objects in the scene separately to 3D formats such as OBJ for my own use. Can I do this?
@harrygraves6870
Ай бұрын
When creating the environment I get "done" as far as the diff_gaussian_rasterisation step, where I get an error. Have tried all the proposed solutions on the Github issues page, and have made sure I am running the correct version of each and every dependancy and nothing works. Does anyone have a definitive guide on how to get this fixed? Thanks.
@j_lee_design
11 ай бұрын
I keep running into issues where: diff-gaussian-rasterization (setup.py) simple-knn (setup.py) both come up with errors after running: conda env create --file environment.yml
@thenerfguru
11 ай бұрын
People are having a lot of luck with this for troubleshooting: github.com/graphdeco-inria/gaussian-splatting/issues/146
@j_lee_design
11 ай бұрын
@@thenerfguru I tried that, doesn’t seem to be working unfortunately. Also “conda activate Gaussian splatting” doesn’t work at all (I don’t have the exact command in front of me so apologies if the syntax is wrong there)- I get an error that “activate” is not a valid command
@thenerfguru
11 ай бұрын
Hmmm. Certainly seems like Anaconda is not in your path. Check this out: saturncloud.io/blog/adding-anaconda-to-your-path-a-guide-for-data-scientists/#:~:text=During%20Anaconda%20Installation%3A%20During%20the,editing%20your%20system's%20environment%20variables.
@wlyiu4057
11 ай бұрын
Is it possible to use two GPUs? I have two 4080s each with 16GB.
@thenerfguru
11 ай бұрын
I am not sure...I would ask that question in the main GitHub repository discussion.
@TunahanBayrak
4 ай бұрын
I have a 2 problem but i can not solve myselft. 1)My -plyfile empty in environment.yml and i did not solve. i tried to many times to install but it's not work my computer. 2)CondaEnvException: Pip failed. I saw some solution but i did not fix the problem Any help?
@BrunoPiresBPS
11 ай бұрын
Do you need like a iphone Pro to make the images to utilize? Because of the "laser" thing? or can be any footage, recording for any device?
@thenerfguru
11 ай бұрын
Any photo. No lidar is involved.
@renanmonteirobarbosa8129
Ай бұрын
You need a tutorial building everything from source to run on Linux Distro.
@danacarvey
11 ай бұрын
Hello, I don't have an RTX 3090 but I do have 2 x RTX 3080ti Will the software take advantage of dual GPUs?
@thenerfguru
11 ай бұрын
Unsure if you can utilize 2 GPUs. There is an early thread in GitHubs Issues where someone mentioned only one GPU can be used. Unsure if that is still the case. I suggest asking in the GitHub discussion board.
@danacarvey
11 ай бұрын
Thanks for your reply@@thenerfguru ! I'm happy with my first test here - kzitem.info/news/bejne/tnugk22jqomSapw
@BlaiGraell-kh4wq
11 ай бұрын
Wow!! this is really amazing. I'm new to Radiance Field methods and this is mind blowing. It's the future of all audiovisual industry. Also your tutorial is so incredibly detailed and well explained. Unfortunately I reached a point from which I couldn't continue because I work on Mac. Do you know if there's any resource where we could learn how to use gaussian splatting on an M1max macbook? Thank you very much in advance
@thenerfguru
11 ай бұрын
For you, your best bet is use Luma AI’s new free Gaussian splats.
@BlaiGraell-kh4wq
11 ай бұрын
That sounds really promissing, I'll give it a try. Thank you so much for taking the time to answer all the questions so fast
@timiles8659
10 ай бұрын
For me the initial install failed and restarting fixed it also! Thanks for making this tutorial :)
@AIWarper
10 ай бұрын
how did you restart it if it already created the conda env? Did you delete the env first? I got a few errors on my install but it did finish
@timiles8659
10 ай бұрын
yup, I first had to do conda env remove -n gaussian_splatting and then re-run (after restarting)@@AIWarper
@AIWarper
10 ай бұрын
Got it working after thanks!@@timiles8659
@thenerfguru
10 ай бұрын
You’re welcome!
@zehrakoc8518
4 ай бұрын
Is Gaussian Splatting considerably different from instant NeRF? My results did not make a remarkable change for the same dataset.
@topvirtualtourscom
11 ай бұрын
Hi, after starting training iI always get this line: Loading Training Cameras [30/09 14:41:23] [ INFO ] Encountered quite large input images (>1.6K pixels width), rescaling to 1.6K. If this is not desired, please explicitly specify '--resolution/-r' as 1 [30/09 14:41:23] Loading Test Cameras [30/09 14:43:54] Number of points at initialisation : 172044 [30/09 14:43:54] This part (INFO) Encountered quite large input images... Should I resize them or just leave as it is? Thanks.
@Snikabarz
11 ай бұрын
I'm getting this error when trying to run "python convert.py -s " 'colmap' is not recognized as an internal or external command, operable program or batch file. ERROR:root:Feature extraction failed with code 1. Exiting." Do you know how i can solve this?
@thenerfguru
11 ай бұрын
Sounds like one of two things: 1. COLMAP was not installed 2. COLMAP was installed and not added to path I address COLMAP at this section of the video: kzitem.info/news/bejne/to6q252dspGojJgsi=ZQ168zOziKEm5vtj&t=472
Пікірлер: 685