Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Rendering

TL;DR

Tensor4D introduces a hierarchical 4D tensor decomposition technique that efficiently models dynamic scenes, enabling high-quality reconstruction and rendering from limited camera views with reduced memory usage.

Contribution

The paper proposes a novel hierarchical 4D tensor decomposition method for dynamic scene modeling, improving efficiency and quality over prior approaches.

Findings

Achieves high-quality dynamic reconstruction from sparse views

Effectively captures structural motions and detailed changes

Validated on synthetic and real-world scenes

Abstract

We present Tensor4D, an efficient yet effective approach to dynamic scene modeling. The key of our solution is an efficient 4D tensor decomposition method so that the dynamic scene can be directly represented as a 4D spatio-temporal tensor. To tackle the accompanying memory issue, we decompose the 4D tensor hierarchically by projecting it first into three time-aware volumes and then nine compact feature planes. In this way, spatial information over time can be simultaneously captured in a compact and memory-efficient manner. When applying Tensor4D for dynamic scene reconstruction and rendering, we further factorize the 4D fields to different scales in the sense that structural motions and dynamic detailed changes can be learned from coarse to fine. The effectiveness of our method is validated on both synthetic and real-world scenes. Extensive experiments show that our method is able to achieve high-quality dynamic reconstruction and rendering from sparse-view camera rigs or even a monocular camera. The code and dataset will be released at https://liuyebin.com/tensor4d/tensor4d.html.