mlsanityData to 14 Oct 2026

NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild

arXiv 2405.18715 ↗First posted 29 May 2024cs.CVcited by 85

Not on the map. Why?

Abstract (arXiv)

Neural Radiance Fields (NeRFs) have shown remarkable success in synthesizing photorealistic views from multi-view images of static scenes, but face challenges in dynamic, real-world environments with distractors like moving objects, shadows, and lighting changes. Existing methods manage controlled environments and low occlusion ratios but fall short in render quality, especially under high occlusion scenarios. In this paper, we introduce NeRF On-the-go, a simple yet effective approach that enables the robust synthesis of novel views in complex, in-the-wild scenes from only casually captured image sequences. Delving into uncertainty, our method not only efficiently eliminates distractors, even when they are predominant in captures, but also achieves a notably faster convergence speed. Through comprehensive experiments on various scenes, our method demonstrates a significant improvement over state-of-the-art techniques. This advancement opens new avenues for NeRF in diverse and dynamic real-world applications.

Key facts. Cited by 85 papers in the map (data through 14 Oct 2026). Builds on 55 of its 64 references that are in the map. First posted on arXiv 29 May 2024.

Builds on

55 of 64 references.

References · 55

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2023Segment Anythingcited by 8,234
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  6. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  7. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  8. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  9. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 806
  10. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 751
  11. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 724
  12. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
38 more
  1. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
  2. 2016Direct Sparse Odometrycited by 485
  3. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  4. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  5. 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
  6. 2022Kubric: A scalable dataset generatorcited by 381
  7. 2020Neural Radiance Flow for 4D View Synthesis and Video Processingcited by 270
  8. 2021Urban Radiance Fieldscited by 263
  9. 2023EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervisioncited by 217
  10. 2020D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometrycited by 206
  11. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  12. 2022SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Imagecited by 165
  13. 2022D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Videocited by 137
  14. 2018DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenescited by 134
  15. 2021Hallucinated Neural Radiance Fields in the Wildcited by 130
  16. 2022ActiveNeRF: Learning where to See with Uncertainty Estimationcited by 127
  17. 2018CubeSLAM: Monocular 3D Object SLAMcited by 102
  18. 2023RobustNeRF: Ignoring Distractors with Robust Lossescited by 101
  19. 2022ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wildcited by 92
  20. 2018DS-SLAM: A Semantic Visual SLAM towards Dynamic Environmentscited by 91
  21. 2023Bayes' Rays: Uncertainty Quantification for Neural Radiance Fieldscited by 91
  22. 2021Neural Trajectory Fields for Dynamic Novel View Synthesiscited by 86
  23. 2022KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypointscited by 77
  24. 2021NeuralDiff: Segmenting 3D objects that move in egocentric videoscited by 57
  25. 2022NeurAR: Neural Uncertainty for Autonomous 3D Reconstruction with Implicit Neural Representationscited by 55
  26. 2023NeU-NBV: Next Best View Planning Using Uncertainty Estimation in Image-Based Neural Renderingcited by 54
  27. 2018Efficient Uncertainty Estimation for Semantic Segmentation in Videoscited by 46
  28. 2020VDO-SLAM: A Visual Dynamic Object-aware SLAM Systemcited by 40
  29. 2022Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimationcited by 28
  30. 2022DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic Environmentscited by 27
  31. 2022PVO: Panoptic Visual Odometrycited by 26
  32. 2022Gradient-based Uncertainty for Monocular Depth Estimationcited by 26
  33. 2023S3IM: Stochastic Structural SIMilarity and Its Unreasonable Effectiveness for Neural Fieldscited by 25
  34. 2021Deep Deterministic Uncertainty for Semantic Segmentationcited by 24
  35. 2019Robust Dense Mapping for Large-Scale Dynamic Environmentscited by 21
  36. 2023UncLe-SLAM: Uncertainty Learning for Dense Neural SLAMcited by 19
  37. 2023DebSDF: Delving into the Details and Bias of Neural Indoor Scene Reconstructioncited by 17
  38. 2023Estimating 3D Uncertainty Field: Quantifying Uncertainty for Neural Radiance Fieldscited by 15

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 18; 2025: 37; 2026: 30.

85 papers.

Sort:

By area:

  1. 2024WildGaussians: 3D Gaussian Splatting in the Wildcited by 152
  2. 2024ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Modelcited by 143
  3. 2024SpotlessSplats: Ignoring Distractors in 3D Gaussian Splattingcited by 61
  4. 2025WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environmentscited by 50
  5. 2024DreamDrive: Generative 4D Scene Modeling from Street View Imagescited by 35
  6. 2024NerfBaselines: Consistent and Reproducible Evaluation of Novel View Synthesis Methodscited by 26
  7. 2025DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagerycited by 22
  8. 2025Emergent Outlier View Rejection in Visual Geometry Grounded Transformerscited by 22
  9. 2024RoMo: Robust Motion Segmentation Improves Structure from Motioncited by 20
  10. 2025Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splattingcited by 20
  11. 2024DeRainGS: Gaussian Splatting for Enhanced Scene Reconstruction in Rainy Environmentscited by 19
  12. 2025RealX3D: A Physically-Degraded 3D Benchmark for Multi-view Visual Restoration and Reconstructioncited by 19
38 more
  1. 2024HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splattingcited by 16
  2. 2025DeGauss: Dynamic-Static Decomposition with Gaussian Splatting for Distractor-free 3D Reconstructioncited by 16
  3. 2024DeSplat: Decomposed Gaussian Splatting for Distractor-Free Renderingcited by 15
  4. 2024T-3DGS: Removing Transient Objects for 3D Scene Reconstructioncited by 13
  5. 2025Neural Radiance Fields for the Real World: A Surveycited by 12
  6. 2025RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGScited by 11
  7. 2025GaussianUpdate: Continual 3D Gaussian Splatting Update for Changing Environmentscited by 11
  8. 2024Sources of Uncertainty in 3D Scene Reconstructioncited by 10
  9. 2026DROID-SLAM in the Wildcited by 10
  10. 2025GaussHDR: High Dynamic Range Gaussian Splatting via Learning Unified 3D and 2D Local Tone Mappingcited by 9
  11. 2025Learning-based 3D Reconstruction in Autonomous Driving: A Comprehensive Surveycited by 9
  12. 2024OccFusion: Rendering Occluded Humans with Generative Diffusion Priorscited by 8
  13. 2024Distractor-free Generalizable 3D Gaussian Splattingcited by 8
  14. 2024NexusSplats: Efficient 3D Gaussian Splatting in the Wildcited by 7
  15. 2025Seg-Wild: Interactive Segmentation based on 3D Gaussian Splatting for Unconstrained Image Collectionscited by 7
  16. 2024MCGS: Multiview Consistency Enhancement for Sparse-View 3D Gaussian Radiance Fieldscited by 6
  17. 2025ForestSplats: Deformable transient field for Gaussian Splatting in the Wildcited by 6
  18. 2025UP-SLAM: Adaptively Structured Gaussian SLAM with Uncertainty Prediction in Dynamic Environmentscited by 6
  19. 2025Robust Neural Rendering in the Wild with Asymmetric Dual 3D Gaussian Splattingcited by 6
  20. 2025WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusioncited by 6
  21. 2024SimVS: Simulating World Inconsistencies for Robust View Synthesiscited by 5
  22. 2025EgoSplat: Open-Vocabulary Egocentric Scene Understanding with Language Embedded 3D Gaussian Splattingcited by 4
  23. 2025EA3D: Online Open-World 3D Object Extraction from Streaming Videoscited by 4
  24. 2026WildRayZer: Self-supervised Large View Synthesis in Dynamic Environmentscited by 4
  25. 2026Evidential Neural Radiance Fieldscited by 4
  26. 2024Uni-SLAM: Uncertainty-Aware Neural Implicit SLAM for Real-Time Dense Indoor Scene Reconstructioncited by 3
  27. 2025MVGSR: Multi-View Consistency Gaussian Splatting for Robust Surface Reconstructioncited by 3
  28. 2025SDD-4DGS: Static-Dynamic Aware Decoupling in Gaussian Splatting for 4D Scene Reconstructioncited by 3
  29. 2025ImViD: Immersive Volumetric Videos for Enhanced VR Engagementcited by 3
  30. 2025Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesiscited by 3
  31. 2025Compensating Spatiotemporally Inconsistent Observations for Online Dynamic 3D Gaussian Splattingcited by 3
  32. 2025WarpRF: Multi-View Consistency for Training-Free Uncertainty Quantification and Applications in Radiance Fieldscited by 3
  33. 2025Robust Low-light Scene Restoration via Illumination Transitioncited by 3
  34. 2025RGE-GS: Reward-Guided Expansive Driving Scene Reconstruction via Diffusion Priorscited by 2
  35. 2025VDEGaussian: Video Diffusion Enhanced 4D Gaussian Splatting for Dynamic Urban Scenes Modelingcited by 2
  36. 2025UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstructioncited by 2
  37. 2024PH-Dropout: Practical Epistemic Uncertainty Quantification for View Synthesiscited by 1
  38. 2025Veta-GS: View-dependent deformable 3D Gaussian Splatting for thermal infrared Novel-view Synthesiscited by 1

50 most cited of 85 All 85 (JSON)