mlsanityData to 7 Oct 2026

NexusSplats: Efficient 3D Gaussian Splatting in the Wild

arXiv 2411.14514 ↗First posted 21 Nov 2024cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Photorealistic 3D reconstruction of unstructured real-world scenes remains challenging due to complex illumination variations and transient occlusions. Existing methods based on Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) struggle with inefficient light decoupling and structure-agnostic occlusion handling. To address these limitations, we propose NexusSplats, an approach tailored for efficient and high-fidelity 3D scene reconstruction under complex lighting and occlusion conditions. In particular, NexusSplats leverages a hierarchical light decoupling strategy that performs centralized appearance learning, efficiently and effectively decoupling varying lighting conditions. Furthermore, a structure-aware occlusion handling mechanism is developed, establishing a nexus between 3D and 2D structures for fine-grained occlusion handling. Experimental results demonstrate that NexusSplats achieves state-of-the-art rendering quality and reduces the number of total parameters by 65.4%, leading to 2.7× faster reconstruction.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 43 of its 59 references that are in the map. First posted on arXiv 21 Nov 2024.

Builds on

43 of 59 references.

References · 43

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  5. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  6. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  7. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  8. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  9. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  10. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  11. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  12. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
31 more
  1. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  2. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  3. 2020Neural Sparse Voxel Fieldscited by 959
  4. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 742
  5. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 684
  6. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  7. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 661
  8. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 596
  9. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  10. 2023LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPScited by 420
  11. 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 365
  12. 2021Urban Radiance Fieldscited by 263
  13. 2023Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesiscited by 232
  14. 2024VastGaussian: Vast 3D Gaussians for Large Scene Reconstructioncited by 209
  15. 2024WildGaussians: 3D Gaussian Splatting in the Wildcited by 150
  16. 2023Compact 3D Scene Representation via Self-Organizing Gaussian Gridscited by 147
  17. 2021Hallucinated Neural Radiance Fields in the Wildcited by 130
  18. 2023CompGS: Smaller and Faster Gaussian Splatting with Vector Quantizationcited by 127
  19. 2024Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collectionscited by 117
  20. 2021NeRF for Outdoor Scene Relightingcited by 114
  21. 2023RobustNeRF: Ignoring Distractors with Robust Lossescited by 101
  22. 2018CGNet: A Light-weight Context Guided Network for Semantic Segmentationcited by 94
  23. 2024NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wildcited by 85
  24. 2024SWAG: Splatting in the Wild images with Appearance-conditioned Gaussianscited by 61
  25. 2024SpotlessSplats: Ignoring Distractors in 3D Gaussian Splattingcited by 61
  26. 2023Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedracited by 57
  27. 2024Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collectionscited by 56
  28. 2023Cross-Ray Neural Radiance Fields for Novel-view Synthesis from Unconstrained Image Collectionscited by 54
  29. 2024WE-GS: An In-the-wild Efficient 3D Gaussian Representation for Unconstrained Photo Collectionscited by 33
  30. 2024Splatfacto-W: A Nerfstudio Implementation of Gaussian Splatting for Unconstrained Photo Collectionscited by 28
  31. 2024NerfBaselines: Consistent and Reproducible Evaluation of Novel View Synthesis Methodscited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 5.

7 papers.

  1. 2025RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGScited by 10
  2. 2025ForestSplats: Deformable transient field for Gaussian Splatting in the Wildcited by 6
  3. 2026LightCity: An Urban Dataset for Outdoor Inverse Rendering and Reconstruction under Multi-illumination Conditionscited by 4
  4. 2026Generalizable Sparse-View 3D Reconstruction from Unconstrained Imagescited by 1
  5. 2026DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesiscited by 0
  6. 2026Difix3D-W: Distractor-Free Few-Shot 3D Gaussian Splatting in the Wildcited by 0
  7. 2026Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarioscited by 0