Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstruction
arXiv:2103.16341
Abstract
This paper focuses on the task of 4D shape reconstruction from a sequence of point clouds. Despite the recent success achieved by extending deep implicit representations into 4D space, it is still a great challenge in two respects, i.e. how to design a flexible framework for learning robust spatio-temporal shape representations from 4D point clouds, and develop an efficient mechanism for capturing shape dynamics. In this work, we present a novel pipeline to learn a temporal evolution of the 3D human shape through spatially continuous transformation functions among cross-frame occupancy fields. The key idea is to parallelly establish the dense correspondence between predicted occupancy fields at different time steps via explicitly learning continuous displacement vector fields from robust spatio-temporal shape representations. Extensive comparisons against previous state-of-the-arts show the superior accuracy of our approach for 4D human reconstruction in the problems of 4D shape auto-encoding and completion, and a much faster network inference with about 8 times speedup demonstrates the significant efficiency of our approach. The trained models and implementation code are available at https://github.com/tangjiapeng/LPDC-Net.
arXiv comment15 pages, 11 figures, CVPR2021
References in corpus (8)
- Point-Set Registration: Coherent Point Drift
- Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images
- High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference
- Video Based Reconstruction of 3D People Models
- Temporally coherent 4D reconstruction of complex dynamic scenes
- A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Images
- SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces from RGB Images
- Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point Clouds