Worth-reading papers and related awesome resources on 3D generation issues. Mainly focused on deep-learning approach. 值得一读的深度学习3D生成论文与相关资源。
Recent years have seen remarkable progress in deep learning powered visual content creation. This includes 3D-aware generative image synthesis, which produces high-fidelity images in a 3D-consistent manner while simultaneously capturing compact surfaces of objects from pure image collections without the need for any 3D supervision, thus bridging the gap between 2D imageryand 3D reality. -Xia et.al
Survey papers
- A Survey on 3D-aware Image Synthesis, arXiv
Weihao Xia, Jing Xue, 2022.10 | [arXiv pdf]
This section mainly focuses on methods that aim to render novel views by learning a deep neural representation from multi-view image collections of a scene or object.
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis, ECCV 2020 -NeRF
Ben Mildenhall, Pratul P. Srinivasan, Matthew Tancik, Jonathan T. Barron, Ravi Ramamoorthi, Ren Ng, 2020.3 | [ECCV pdf] [arXiv pdf] [Project homepage] [Official implementation (TF)]