NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation
This addresses a key limitation for 3D reconstruction and view synthesis applications, but is incremental as it builds on existing NeRF and segmentation methods.
The paper tackles the problem of Neural Radiance Fields (NeRF) producing artifacts in non-static scenes due to transient distractors like moving objects, and proposes Heuristics-Guided Segmentation (HuGS) to enhance separation of static scenes, showing superiority and robustness in experiments.
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/.