2D GANs Meet Unsupervised Single-view 3D Reconstruction

TL;DR

This paper introduces a novel method combining 2D GAN-generated images and neural implicit functions for unsupervised single-view 3D reconstruction, improving accuracy by handling unreliable supervisions.

Contribution

It presents a new offline StyleGAN-based generator for view-controlled pseudo images and an uncertainty module to enhance 3D reconstruction from single images.

Findings

Achieves superior single-view 3D reconstruction results.

Effectively handles unreliable supervisions with the uncertainty module.

Demonstrates the method's effectiveness on generic objects.

Abstract

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.