Point-Based Radiance Fields for Controllable Human Motion Synthesis

TL;DR

This paper introduces a new method for controllable human motion synthesis using point-based radiance fields, enabling detailed 3D editing and deformation with high fidelity and generalization to various characters.

Contribution

The proposed approach combines static point cloud training with deformation encoding via MLP and local rotation estimation, enabling complex 3D human editing beyond previous methods.

Findings

Outperforms state-of-the-art in fine-level complex deformation

Generalizes well to non-human 3D characters

Maintains consistency with canonical space training

Abstract

This paper proposes a novel controllable human motion synthesis method for fine-level deformation based on static point-based radiance fields. Although previous editable neural radiance field methods can generate impressive results on novel-view synthesis and allow naive deformation, few algorithms can achieve complex 3D human editing such as forward kinematics. Our method exploits the explicit point cloud to train the static 3D scene and apply the deformation by encoding the point cloud translation using a deformation MLP. To make sure the rendering result is consistent with the canonical space training, we estimate the local rotation using SVD and interpolate the per-point rotation to the query view direction of the pre-trained radiance field. Extensive experiments show that our approach can significantly outperform the state-of-the-art on fine-level complex deformation which can be generalized to other 3D characters besides humans.