Template-free Articulated Neural Point Clouds for Reposable View Synthesis

TL;DR

This paper introduces a point-based, skeletal-aware neural rendering method that synthesizes high-fidelity, reposable views of articulated objects efficiently, without requiring object-specific templates or extensive training.

Contribution

It proposes a novel joint learning framework for Dynamic NeRF and skeletal models using linear blend skinning, enabling reposable view synthesis from sparse multi-view videos.

Findings

Achieves state-of-the-art visual fidelity in novel view synthesis.

Reduces training time compared to existing dynamic NeRF methods.

Produces reposable 3D reconstructions without object-specific templates.

Abstract

Dynamic Neural Radiance Fields (NeRFs) achieve remarkable visual quality when synthesizing novel views of time-evolving 3D scenes. However, the common reliance on backward deformation fields makes reanimation of the captured object poses challenging. Moreover, the state of the art dynamic models are often limited by low visual fidelity, long reconstruction time or specificity to narrow application domains. In this paper, we present a novel method utilizing a point-based representation and Linear Blend Skinning (LBS) to jointly learn a Dynamic NeRF and an associated skeletal model from even sparse multi-view video. Our forward-warping approach achieves state-of-the-art visual fidelity when synthesizing novel views and poses while significantly reducing the necessary learning time when compared to existing work. We demonstrate the versatility of our representation on a variety of articulated objects from common datasets and obtain reposable 3D reconstructions without the need of object-specific skeletal templates. Code will be made available at https://github.com/lukasuz/Articulated-Point-NeRF.