NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation

TL;DR

NeRF-HuGS introduces a heuristics-guided segmentation approach that effectively separates static scene elements from transient distractors, improving neural radiance fields in dynamic environments.

Contribution

The paper presents a novel heuristics-guided segmentation paradigm combining SfM and color residual heuristics to enhance NeRF performance in non-static scenes.

Findings

Significantly reduces artifacts caused by moving objects in NeRF reconstructions.

Outperforms previous methods in robustness across diverse dynamic scenes.

Demonstrates improved scene reconstruction quality in experiments.

Abstract

Neural Radiance Field (NeRF) has been widely recognized for its excellence in novel view synthesis and 3D scene reconstruction. However, their effectiveness is inherently tied to the assumption of static scenes, rendering them susceptible to undesirable artifacts when confronted with transient distractors such as moving objects or shadows. In this work, we propose a novel paradigm, namely "Heuristics-Guided Segmentation" (HuGS), which significantly enhances the separation of static scenes from transient distractors by harmoniously combining the strengths of hand-crafted heuristics and state-of-the-art segmentation models, thus significantly transcending the limitations of previous solutions. Furthermore, we delve into the meticulous design of heuristics, introducing a seamless fusion of Structure-from-Motion (SfM)-based heuristics and color residual heuristics, catering to a diverse range of texture profiles. Extensive experiments demonstrate the superiority and robustness of our method in mitigating transient distractors for NeRFs trained in non-static scenes. Project page: https://cnhaox.github.io/NeRF-HuGS/.