Gengshan Yang 1 Deqing Sun 2 Varun Jampani 2 Daniel Vlasic 2 Forrester Cole 2 Huiwen Chang 2 Deva Ramanan 1 William T. Freeman 2 Ce Liu 2 1 Carnegie Mellon University 2 Google Research
Remarkable progress has been made in 3D reconstruction of rigid structures from a video or a collection of images. However, it is still challenging to reconstruct nonrigid structures from RGB inputs, due to the under-constrained nature of this problem. While template-based approaches, such as parametric shape models, have achieved great success in terms of modeling the ``closed world" of known object categories, their ability to handle the ``open-world" of novel object categories and outlier shapes is still
Neural Dense Non-Rigid Structure from Motion with Latent Space Constraints. ECCV 2020. Learning Category-Specific Mesh Reconstruction from Image Collections. ECCV 2018. Self-supervised Single-view 3D Reconstruction via Semantic Consistency. ECCV 2020. Shape and Viewpoints without Keypoints. ECCV. 2020. Articulation Aware Canonical Surface Mapping. CVPR 2020. Creatures great and SMAL: Recovering the shape and motion of animals from video. ACCV 2018. Three-D Safari: Learning to Estimate Zebra Pose, Shape, and