NeRF-HuGS

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.

Heuristics-Guided Segmentation (HuGS)

Pipeline of HuGS: (a) Given unordered images of a static scene disturbed by transient distractors as input, we first obtain two types of heuristics. (b) SfM-based heuristics use SfM to distinguish between static (green) and transient features (red). The static features are then employed as point prompts to generate dense masks using SAM. (c) Residual-based heuristics are based on a partially trained NeRF (ie, trained for several thousands of iterations) that can provide reasonable color residuals. (d) Their combination finally guides SAM again to generate (e) the static map for each input image.

Visualization: Here are examples of HuGS on different scenes (datasets). More results can be found in the paper and the data.

(1) Input

(2) Seg. w/ SfM

(3) H^SfM

(4) Color Residual

(5) H^CR

(6) Static Map

Rendering Results

Comparisons on the Distractor Dataset: Our method can better preserve static details while ignoring transient distractors.

BabyYoda

Mip-NeRF 360

w/ RobustNeRF

w/ HuGS (ours)

Crab

Statue

Android

Comparisons on the Kubric Dataset:

Pillow

Mip-NeRF 360

w/ RobustNeRF

w/ HuGS (ours)

Chairs

Cars

Comparisons on the Phototourism Dataset:

Brandenburg Gate

Mip-NeRF 360

w/ RobustNeRF

w/ HuGS (ours)

Sacre Coeur

Taj Mahal

Trevi Fountain

BibTeX

@article{chen2024nerfhugs,
  author    = {Chen, Jiahao and Qin, Yipeng and Liu, Lingjie and Lu, Jiangbo and Li, Guanbin},
  title     = {NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation},
  journal   = {CVPR},
  year      = {2024},
}