Log In Sign Up

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

by   Jiapeng Tang, et al.

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


page 8

page 10

page 13


ASAP-Net: Attention and Structure Aware Point Cloud Sequence Segmentation

Recent works of point clouds show that mulit-frame spatio-temporal model...

One Framework to Register Them All: PointNet Encoding for Point Cloud Alignment

PointNet has recently emerged as a popular representation for unstructur...

Representation-Agnostic Shape Fields

3D shape analysis has been widely explored in the era of deep learning. ...

Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions

The problems of shape classification and part segmentation from 3D point...

Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds

To date, various 3D scene understanding tasks still lack practical and g...

Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence

The goal of this paper is to learn dense 3D shape correspondence for top...

Code Repositories


CVPR2021 paper "Learning Parallel Dense Correspondence from Spatio-Temporal Descriptorsfor Efficient and Robust 4D Reconstruction"

view repo