Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstruction

TL;DR

This paper introduces a novel method for 4D shape reconstruction that learns dense spatio-temporal correspondences, achieving higher accuracy and significantly faster inference in 4D human shape modeling from point cloud sequences.

Contribution

It proposes a new pipeline that explicitly learns continuous displacement fields for robust and efficient 4D shape reconstruction from point clouds.

Findings

Outperforms previous methods in accuracy for 4D human reconstruction

Achieves about 8 times faster inference speed

Demonstrates superior performance in shape auto-encoding and completion

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.