mlsanityData to 7 Oct 2026

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

arXiv 2403.17537 ↗First posted 26 Mar 2024cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

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/.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 47 of its 58 references that are in the map. First posted on arXiv 26 Mar 2024.

Builds on

47 of 58 references.

References · 47

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2023Segment Anythingcited by 8,158
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  5. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  6. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  7. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  8. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  9. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  10. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  11. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  12. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
35 more
  1. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  2. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  3. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
  4. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  5. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  6. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  7. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 730
  8. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  9. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
  10. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 596
  11. 2021Neural Fields in Visual Computing and Beyondcited by 539
  12. 2023LERF: Language Embedded Radiance Fieldscited by 538
  13. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 464
  14. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  15. 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 411
  16. 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 396
  17. 2022Kubric: A scalable dataset generatorcited by 373
  18. 2021Urban Radiance Fieldscited by 263
  19. 2023Robust Dynamic Radiance Fieldscited by 193
  20. 2022Panoptic Lifting for 3D Scene Understanding with Neural Fieldscited by 171
  21. 2022SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fieldscited by 144
  22. 2022D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Videocited by 136
  23. 2021Hallucinated Neural Radiance Fields in the Wildcited by 130
  24. 2021NeRF for Outdoor Scene Relightingcited by 114
  25. 2023RobustNeRF: Ignoring Distractors with Robust Lossescited by 101
  26. 2023Neural Fields meet Explicit Geometric Representation for Inverse Rendering of Urban Scenescited by 89
  27. 2022Neural 3D Reconstruction in the Wildcited by 79
  28. 2022Removing Objects From Neural Radiance Fieldscited by 66
  29. 2023Temporal Interpolation Is All You Need for Dynamic Neural Radiance Fieldscited by 59
  30. 2022ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Fieldcited by 37
  31. 2023OR-NeRF: Object Removing from 3D Scenes Guided by Multiview Segmentation with Neural Radiance Fieldscited by 34
  32. 2023AutoRecon: Automated 3D Object Discovery and Reconstructioncited by 13
  33. 2023UP-NeRF: Unconstrained Pose-Prior-Free Neural Radiance Fieldscited by 12
  34. 2023Neural Scene Chronologycited by 10
  35. 2023Semantic-aware Occlusion Filtering Neural Radiance Fields in the Wildcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 7; 2026: 11.

25 papers.

Sort:

By area:

  1. 2024SpotlessSplats: Ignoring Distractors in 3D Gaussian Splattingcited by 61
  2. 2024DreamDrive: Generative 4D Scene Modeling from Street View Imagescited by 35
  3. 2025DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagerycited by 20
  4. 2024HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splattingcited by 16
  5. 2025DeGauss: Dynamic-Static Decomposition with Gaussian Splatting for Distractor-free 3D Reconstructioncited by 16
  6. 2024DeSplat: Decomposed Gaussian Splatting for Distractor-Free Renderingcited by 15
  7. 2024T-3DGS: Removing Transient Objects for 3D Scene Reconstructioncited by 13
  8. 2025RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGScited by 10
  9. 2024SPARS3R: Semantic Prior Alignment and Regularization for Sparse 3D Reconstructioncited by 8
  10. 2024Distractor-free Generalizable 3D Gaussian Splattingcited by 8
  11. 2025EgoSplat: Open-Vocabulary Egocentric Scene Understanding with Language Embedded 3D Gaussian Splattingcited by 4
  12. 2026WildRayZer: Self-supervised Large View Synthesis in Dynamic Environmentscited by 4
13 more
  1. 2025MVGSR: Multi-View Consistency Gaussian Splatting for Robust Surface Reconstructioncited by 3
  2. 2025A Constrained Optimization Approach for Gaussian Splatting from Coarsely-posed Images and Noisy Lidar Point Cloudscited by 1
  3. 2025OCSplats: Observation Completeness Quantification and Label Noise Separation in 3DGScited by 1
  4. 2026WilLaGS: Latent-Conditional 3D Appearance Fields for Robust Gaussian Splatting In-the-Wildcited by 1
  5. 2026WildGHand: Learning Anti-Perturbation Gaussian Hand Avatars from Monocular In-the-Wild Videoscited by 0
  6. 2026Sparse View Distractor-Free Gaussian Splattingcited by 0
  7. 20263DGS-HPC: Distractor-free 3D Gaussian Splatting with Hybrid Patch-wise Classificationcited by 0
  8. 2026FullCircle: Effortless 3D Reconstruction from Casual 360^circ Capturescited by 0
  9. 2026DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesiscited by 0
  10. 2026MU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scenecited by 0
  11. 2026Difix3D-W: Distractor-Free Few-Shot 3D Gaussian Splatting in the Wildcited by 0
  12. 2026HarmoGS: Robust 3D Gaussian Splatting in the Wild via Conflict-Aware Gradient Harmonizationcited by 0
  13. 2026Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarioscited by 0