Abstract

Object reconstruction from 3D point clouds has achieved impressive progress in the computer vision and computer graphics research field. However, reconstruction from time-varying point clouds (a.k.a. 4D point clouds) is generally overlooked. In this paper, we propose a new network architecture, namely RFNet-4D, that jointly reconstructs objects and their motion flows from 4D point clouds. The key insight is that simultaneously performing both tasks via learning spatial and temporal features from a sequence of point clouds can leverage individual tasks and lead to improved overall performance. The proposed network can be trained using both supervised and unsupervised learning. To prove this ability, we design a temporal vector field learning module using an unsupervised learning approach for flow estimation, leveraged by supervised learning of spatial structures for object reconstruction. Extensive experiments and analyses on benchmark dataset validated the effectiveness and efficiency of our method. As shown in experimental results, our method achieves state-of-the-art performance on both flow estimation and object reconstruction while performing much faster than existing methods in both training and inference.

Video

Overview

Given a sequence of time-varying 3D point clouds (first row), we jointly reconstruct corresponding 3D geometric shapes (second row) and estimate their motion fields for every point cloud (third row).

Our Network Architecture

Network architecture of our Compositional encoder, temporal decoder and occupancy decoder.

Qualitative Results

The first row includes (from left to right): input point cloud, ground truth mesh of entire body, ground truth mesh of upper/lower body, and ground-truth flows (darker vectors show stronger motions). Each following row represents corresponding reconstruction and flow estimation results. Severe errors are highlighted.