mlsanityData to 7 Oct 2026

Micro-macro Wavelet-based Gaussian Splatting for 3D Reconstruction from Unconstrained Images

arXiv 2501.14231 ↗First posted 24 Jan 2025cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

3D reconstruction from unconstrained image collections presents substantial challenges due to varying appearances and transient occlusions. In this paper, we introduce Micro-macro Wavelet-based Gaussian Splatting (MW-GS), a novel approach designed to enhance 3D reconstruction by disentangling scene representations into global, refined, and intrinsic components. The proposed method features two key innovations: Micro-macro Projection, which allows Gaussian points to capture details from feature maps across multiple scales with enhanced diversity; and Wavelet-based Sampling, which leverages frequency domain information to refine feature representations and significantly improve the modeling of scene appearances. Additionally, we incorporate a Hierarchical Residual Fusion Network to seamlessly integrate these features. Extensive experiments demonstrate that MW-GS delivers state-of-the-art rendering performance, surpassing existing methods.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 33 of its 46 references that are in the map. First posted on arXiv 24 Jan 2025.

Builds on

33 of 46 references.

References · 33

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  6. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  7. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  8. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  9. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  10. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 684
  11. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  12. 2017Neural 3D Mesh Renderercited by 437
21 more
  1. 2023PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamicscited by 368
  2. 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 365
  3. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 361
  4. 2023DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenescited by 359
  5. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  6. 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 308
  7. 2023Text-to-3D using Gaussian Splattingcited by 299
  8. 2023MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenescited by 215
  9. 2023Language Embedded 3D Gaussians for Open-Vocabulary Scene Understandingcited by 205
  10. 2023GaussianEditor: Editing 3D Gaussians Delicately with Text Instructionscited by 166
  11. 2024WildGaussians: 3D Gaussian Splatting in the Wildcited by 150
  12. 2024HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splattingcited by 141
  13. 2022VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Gridscited by 133
  14. 2021Hallucinated Neural Radiance Fields in the Wildcited by 130
  15. 2024Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collectionscited by 117
  16. 2019Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformationcited by 103
  17. 2021Local Relation Learning for Face Forgery Detectioncited by 100
  18. 2024SWAG: Splatting in the Wild images with Appearance-conditioned Gaussianscited by 61
  19. 2024Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collectionscited by 56
  20. 2023Cross-Ray Neural Radiance Fields for Novel-view Synthesis from Unconstrained Image Collectionscited by 54
  21. 2024WE-GS: An In-the-wild Efficient 3D Gaussian Representation for Unconstrained Photo Collectionscited by 33

Built on by

Cited by year (2026 to 7 Oct)

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

10 papers.

  1. 2026TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstructioncited by 13
  2. 2025UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collectionscited by 10
  3. 2025From Coarse to Fine: Learnable Discrete Wavelet Transforms for Efficient 3D Gaussian Splattingcited by 6
  4. 2025DWTGS: Rethinking Frequency Regularization for Sparse-view 3D Gaussian Splattingcited by 5
  5. 2025GR-Gaussian: Graph-Based Radiative Gaussian Splatting for Sparse-View CT Reconstructioncited by 5
  6. 2025Micro-macro Gaussian Splatting with Enhanced Scalability for Unconstrained Scene Reconstructioncited by 2
  7. 2025Debiasing Diffusion Priors via 3D Attention for Consistent Gaussian Splattingcited by 1
  8. 2026Learnable Multi-level Discrete Wavelet Transforms for 3D Gaussian Splatting Frequency Modulationcited by 1
  9. 2026Gau-Occ: Geometry-Completed Gaussians for Multi-Modal 3D Occupancy Predictioncited by 1
  10. 2026Catalyst4D: High-Fidelity 3D-to-4D Scene Editing via Dynamic Propagationcited by 0