GaussiGAN: Controllable image synthesis with 3D Gaussians from unposed silhouettes
- Title
- GaussiGAN: Controllable image synthesis with 3D Gaussians from unposed silhouettes
- Authors
- A. Mejjati, Youssef; Milefchik, Isa; Gokaslan, Aaron; Wang, Oliver; KIM, KWANG IN; Tompkin, James
- Date Issued
- 2021-11-23
- Publisher
- The British Machine Vision Association
- Abstract
- We present an algorithm to reconstruct a coarse representation of objects from unposed multi-view 2D mask supervision. Our approach learns to represent object shape and pose with a set of self-supervised canonical 3D anisotropic Gaussians, via a perspective camera and a set of perinstance transforms. We show that this robustly estimates a 3D space for the camera and object, while recent state-of-the-art voxel-based baselines struggle to reconstruct either masks or textures in this setting. We show results on synthetic datasets with realistic lighting, and demonstrate an application of object insertion. This helps move towards structured representations that handle more real-world variation in learned object reconstruction.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/119658
- Article Type
- Conference
- Citation
- British Machine Vision Conference, 2021-11-23
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.