NextFace icon indicating copy to clipboard operation
NextFace copied to clipboard

A high-fidelity 3D face reconstruction library from monocular RGB image(s)

Results 48 NextFace issues
Sort by recently updated
recently updated
newest added
trafficstars

Hey there, thanks for your impressive work! I tried Nextface first and now implemented DeepNextFace by myself, using default resnet152 in pytorch(pretrained on ImageNet), but during step 1, landmark loss...

iterStep1 2000 left Deep3DFaceRecon_pytorch, right NextFace. ![Image 11](https://user-images.githubusercontent.com/72028833/187398831-a022b6c5-0641-4f71-9e81-b573181b9b61.png) ![Image 12](https://user-images.githubusercontent.com/72028833/187398835-e5abef0f-5e53-4cee-82af-2ef49be63c4f.png) ![e5895849736cc2a677c7386e31d6](https://user-images.githubusercontent.com/72028833/187398889-7c5b5d34-d025-4095-849d-f3edf55a59dd.jpeg) iterStep1 10000 ![debug1_iter0_frame0](https://user-images.githubusercontent.com/72028833/187399064-a81bbb07-d1bc-4fac-8cf4-30e4ce637d87.png) ![render_0](https://user-images.githubusercontent.com/72028833/187399143-3dd19bd0-c8b4-441b-b88f-45820e027602.png) ![landmarks0](https://user-images.githubusercontent.com/72028833/187399212-4273a129-1aec-4326-9137-2afc97d2bfba.png)

Thanks for your great works. I want to know the process of calculating uvParametrization.pickle, in order to replace BFM model to FLAME. Looking forward to your detailed answer.

Hi! Thanks for your code. I have some questions about smoothing SH coeffs. I notice that during optimization there is no `smoothSH` operation because the default value of smooth is...

Dear author, Thank you for the great work. During the reproducing process, I noticed that the rendering result is with eye balls, while the paper results do not have that....

Hi, I am new in the AI world and I am sorry for my ingnorance. The question that I have and (I have not found the reponse yet) is why...

Implementation of the following renderers - Mitsuba 3 another differentiable renderer - Vertex based Mitusba is a well documented ray tracing differentiable renderer that supports : - newer graphic cards...

Trying to run the replay.py animation but I'm getting the below error: ``` loading optim config from: ./optimConfig.ini Loading Basel Face Model 2017 from ./baselMorphableModel/morphableModel-2017.pickle... loading mesh normals... loading uv...

`(faceNext) C:\Users\aades\Music\testthings\NextFace>python optimizer.py --sharedIdentity --input C:\Users\aades\Downloads\face --output C:\Users\aades\Downloads\New\ loading optim config from: ./optimConfig.ini [WARN] no cuda enabled device found. switching to cpu... Loading Basel Face Model 2017 from ./baselMorphableModel/morphableModel-2017.pickle... loading...

win 11, 4090 ``` C:\NextFace\landmarksfan.py:35: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting...