Conference proceeding
2D GANs Meet Unsupervised Single-View 3D Reconstruction
COMPUTER VISION - ECCV 2022, PT I, v 13661, pp 497-514
01 Jan 2022
Featured in Collection : UN Sustainable Development Goals @ Drexel
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.
Metrics
Details
- Title
- 2D GANs Meet Unsupervised Single-View 3D Reconstruction
- Creators
- Feng Liu - Drexel University, Computer Science (Computing)Xiaoming Liu - Michigan State University
- Publication Details
- COMPUTER VISION - ECCV 2022, PT I, v 13661, pp 497-514
- Series
- Lecture Notes in Computer Science
- Publisher
- Springer Nature
- Number of pages
- 18
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Computer Science (Computing)
- Web of Science ID
- WOS:000898293500029
- Scopus ID
- 2-s2.0-85142727301
- Other Identifier
- 991021906502404721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Imaging Science & Photographic Technology