Template-free Articulated Neural Point Clouds for Reposable View Synthesis
This addresses the problem of reposable view synthesis for articulated objects in computer vision, offering a versatile solution without object-specific templates, though it is incremental in improving existing dynamic NeRF approaches.
The paper tackles the challenge of reanimating object poses in dynamic Neural Radiance Fields (NeRFs) by introducing a template-free method using point-based representation and Linear Blend Skinning, achieving state-of-the-art visual fidelity and reduced learning time.
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.