mlsanityData to 7 Oct 2026

PlanarSplatting: Accurate Planar Surface Reconstruction in 3 Minutes

arXiv 2412.03451 ↗First posted 4 Dec 2024cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

This paper presents PlanarSplatting, an ultra-fast and accurate surface reconstruction approach for multiview indoor images. We take the 3D planes as the main objective due to their compactness and structural expressiveness in indoor scenes, and develop an explicit optimization framework that learns to fit the expected surface of indoor scenes by splatting the 3D planes into 2.5D depth and normal maps. As our PlanarSplatting operates directly on the 3D plane primitives, it eliminates the dependencies on 2D/3D plane detection and plane matching and tracking for planar surface reconstruction. Furthermore, the essential merits of plane-based representation plus CUDA-based implementation of planar splatting functions, PlanarSplatting reconstructs an indoor scene in 3 minutes while having significantly better geometric accuracy. Thanks to our ultra-fast reconstruction speed, the largest quantitative evaluation on the ScanNet and ScanNet++ datasets over hundreds of scenes clearly demonstrated the advantages of our method. We believe that our accurate and ultrafast planar surface reconstruction method will be applied in the structured data curation for surface reconstruction in the future. The code of our CUDA implementation will be publicly available. Project page: https://icetttb.github.io/PlanarSplatting/

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 28 of its 45 references that are in the map. First posted on arXiv 4 Dec 2024.

Builds on

28 of 45 references.

References · 28

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  3. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  4. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 747
  5. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  6. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
  7. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  8. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  9. 2019Differentiable Surface Splatting for Point-based Geometry Processingcited by 238
  10. 2018PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Imagecited by 105
  11. 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 83
  12. 2018PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Imagecited by 77
16 more
  1. 2019Single-Image Piece-wise Planar 3D Reconstruction via Associative Embeddingcited by 56
  2. 2021Planar Surface Reconstruction from Sparse Viewscited by 40
  3. 20233D Line Mapping Revisitedcited by 39
  4. 2023Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitivescited by 37
  5. 2021PlaneTR: Structure-Guided Transformers for 3D Plane Recoverycited by 33
  6. 2022PlaneMVS: 3D Plane Reconstruction from Multi-View Stereocited by 29
  7. 2022PlanarRecon: Real-time 3D Plane Detection and Reconstruction from Posed Monocular Videoscited by 27
  8. 2022PlaneFormers: From Sparse View Planes to 3D Reconstructioncited by 26
  9. 2022NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstructioncited by 21
  10. 2023PAPR: Proximity Attention Point Renderingcited by 16
  11. 2024AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddingscited by 13
  12. 2023NEAT: Distilling 3D Wireframes from Neural Attraction Fieldscited by 12
  13. 2020From Planes to Corners: Multi-Purpose Primitive Detection in Unorganized 3D Point Cloudscited by 7
  14. 2019Surface Reconstruction from 3D Line Segmentscited by 6
  15. 2024AlphaTablets: A Generic Plane Representation for 3D Planar Reconstruction from Monocular Videoscited by 6
  16. 2019Oriented Point Sampling for Plane Detection in Unorganized Point Cloudscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 5.

13 papers.

Sort:

By area:

  1. 2025G4Splat: Geometry-Guided Gaussian Splatting with Generative Priorcited by 10
  2. 2025PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-Forward Planar Splattingcited by 5
  3. 2025Radiant Triangle Soup with Soft Connectivity Forces for 3D Reconstruction and Novel View Synthesiscited by 2
  4. 20253D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstructioncited by 2
  5. 2026PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstructioncited by 2
  6. 2025GSPlane: Concise and Accurate Planar Reconstruction via Structured Representationcited by 1
  7. 2025From Volume Rendering to 3D Gaussian Splatting: Theory and Applicationscited by 1
  8. 2026Interacted Planes Reveal 3D Line Mappingcited by 1
  9. 2025A Mixed-Primitive-based Gaussian Splatting Method for Surface Reconstructioncited by 0
  10. 2025Top2Pano: Learning to Generate Indoor Panoramas from Top-Down Viewcited by 0
  11. 2026PlanaReLoc: Camera Relocalization in 3D Planar Primitives via Region-Based Structure Matchingcited by 0
  12. 2026TopoGS: Planar Reconstruction via Topology-aware 3D Gaussian Splattingcited by 0
1 more
  1. 2026Pixel-wise Planarity for High-Precision Monocular Plane Segmentationcited by 0