Recent research has shown that controllable image generation based on pre-trained GANs can benefit a wide range of computer vision tasks. However, less attention has been devoted to 3D vision tasks. In light of this, we propose a novel image-conditioned neural implicit field, which can leverage 2D supervisions from GAN-generated multi-view images and perform the single-view reconstruction of generic objects. Firstly, a novel offline StyleGAN-based generator is presented to generate plausible pseudo images with full control over the viewpoint. Then, we propose to utilize a neural implicit function, along with a differentiable renderer to learn 3D geometry from pseudo images with object masks and rough pose initializations. To further detect the unreliable supervisions, we introduce a novel uncertainty module to predict uncertainty maps, which remedy the negative effect of uncertain regions in pseudo images, leading to a better reconstruction performance. The effectiveness of our approach is demonstrated through superior single-view 3D reconstruction results of generic objects.
2D GANs Meet Unsupervised Single-View 3D Reconstruction
Feng Liu, Xiaoming LiuKeywords: 3D Shape Reconstruction, Generic Object 3D Reconstruction
GANSVR Source Code
The source code can be downloaded from here
Publications
-
2D GANs Meet Unsupervised Single-View 3D Reconstruction
Feng Liu, Xiaoming Liu
In Proceeding of European Conference on Computer Vision (ECCV 2022), Tel-Aviv, Israel, Oct. 2022
Bibtex | PDF | arXiv | Supplemental | Code