mlsanityData to 14 Oct 2026

CoMapGS: Covisibility Map-based Gaussian Splatting for Sparse Novel View Synthesis

arXiv 2503.20998 ↗First posted 25 Mar 2025cs.GR cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

We propose Covisibility Map-based Gaussian Splatting (CoMapGS), designed to recover underrepresented sparse regions in sparse novel view synthesis. CoMapGS addresses both high- and low-uncertainty regions by constructing covisibility maps, enhancing initial point clouds, and applying uncertainty-aware weighted supervision using a proximity classifier. Our contributions are threefold: (1) CoMapGS reframes novel view synthesis by leveraging covisibility maps as a core component to address region-specific uncertainty; (2) Enhanced initial point clouds for both low- and high-uncertainty regions compensate for sparse COLMAP-derived point clouds, improving reconstruction quality and benefiting few-shot 3DGS methods; (3) Adaptive supervision with covisibility-score-based weighting and proximity classification achieves consistent performance gains across scenes with varying sparsity scores derived from covisibility maps. Experimental results demonstrate that CoMapGS outperforms state-of-the-art methods on datasets including Mip-NeRF 360 and LLFF.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 35 of its 41 references that are in the map. First posted on arXiv 25 Mar 2025.

Builds on

35 of 41 references.

References · 35

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  3. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  4. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  5. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  6. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
  7. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  8. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  9. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 615
  10. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  11. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 395
  12. 2023ReconFusion: 3D Reconstruction with Diffusion Priorscited by 318
23 more
  1. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 311
  2. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 302
  3. 2023FSGS: Real-Time Few-shot View Synthesis using Gaussian Splattingcited by 279
  4. 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
  5. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  6. 2022SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstructioncited by 216
  7. 2024Mini-Splatting: Representing Scenes with a Constrained Number of Gaussianscited by 213
  8. 2022Monocular Dynamic View Synthesis: A Reality Checkcited by 200
  9. 2021InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Renderingcited by 182
  10. 2023SparseGS: Sparse View Synthesis using 3D Gaussian Splattingcited by 134
  11. 2023DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Modelscited by 127
  12. 2024CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularizationcited by 121
  13. 2022ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformerscited by 70
  14. 2024CoherentGS: Sparse Novel View Synthesis with Coherent 3D Gaussianscited by 62
  15. 2023GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistencycited by 54
  16. 2023SimpleNeRF: Regularizing Sparse Input Neural Radiance Fields with Simpler Solutionscited by 44
  17. 2024MVPGS: Excavating Multi-view Priors for Gaussian Splatting from Sparse Input Viewscited by 29
  18. 2023Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Expertscited by 27
  19. 2023NeRFVS: Neural Radiance Fields for Free View Synthesis via Geometry Scaffoldscited by 16
  20. 2023CaesarNeRF: Calibrated Semantic Representation for Few-shot Generalizable Neural Renderingcited by 10
  21. 2023Global Latent Neural Renderingcited by 9
  22. 2024Few-shot NeRF by Adaptive Rendering Loss Regularizationcited by 6
  23. 2024InfoNorm: Mutual Information Shaping of Normals for Sparse-View Reconstructioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 6.

10 papers.

  1. 2026Map2Thought: Explicit 3D Spatial Reasoning via Metric Cognitive Mapscited by 8
  2. 2025OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splattingcited by 5
  3. 2025Sparse-View 3D Reconstruction: Recent Advances and Open Challengescited by 4
  4. 2026Intrinsic Geometry-Appearance Consistency Optimization for Sparse-View Gaussian Splattingcited by 3
  5. 2026SA-ResGS: Self-Augmented Residual 3D Gaussian Splatting for Next Best View Selectioncited by 2
  6. 2025Initialize to Generalize: A Stronger Initialization Pipeline for Sparse-View 3DGScited by 1
  7. 2025Do Flat Minima Improve Sparse Novel View Synthesis?cited by 1
  8. 2026HeroGS: Hierarchical Guidance for Robust 3D Gaussian Splatting under Sparse Viewscited by 0
  9. 2026PanoPlane: Plane-Aware Panoramic Completion for Sparse-View Indoor 3D Gaussian Splattingcited by 0
  10. 2026TWINGS: Thin Plate Splines Warp-aligned Initialization for Sparse-View Gaussian Splattingcited by 0