mlsanityData to 14 Oct 2026

Dense-SfM: Structure from Motion with Dense Consistent Matching

arXiv 2501.14277 ↗First posted 24 Jan 2025cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

We present Dense-SfM, a novel Structure from Motion (SfM) framework designed for dense and accurate 3D reconstruction from multi-view images. Sparse keypoint matching, which traditional SfM methods often rely on, limits both accuracy and point density, especially in texture-less areas. Dense-SfM addresses this limitation by integrating dense matching with a Gaussian Splatting (GS) based track extension which gives more consistent, longer feature tracks. To further improve reconstruction accuracy, Dense-SfM is equipped with a multi-view kernelized matching module leveraging transformer and Gaussian Process architectures, for robust track refinement across multi-views. Evaluations on the ETH3D and Texture-Poor SfM datasets show that Dense-SfM offers significant improvements in accuracy and density over state-of-the-art methods. Project page: https://icetea-cv.github.io/densesfm/.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 48 of its 79 references that are in the map. First posted on arXiv 24 Jan 2025.

Builds on

48 of 79 references.

References · 48

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  6. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  7. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  8. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  9. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  10. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  11. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  12. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 559
36 more
  1. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 388
  2. 2020DISK: Learning local features with policy gradientcited by 312
  3. 2023RoMa: Robust Dense Feature Matchingcited by 302
  4. 2023FSGS: Real-Time Few-shot View Synthesis using Gaussian Splattingcited by 279
  5. 20243D Reconstruction with Spatial Memorycited by 277
  6. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 264
  7. 2020Image Matching across Wide Baselines: From Paper to Practicecited by 225
  8. 2024Global Structure-from-Motion Revisitedcited by 218
  9. 2022Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstructioncited by 212
  10. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 207
  11. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 200
  12. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 171
  13. 2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 162
  14. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 157
  15. 2024WildGaussians: 3D Gaussian Splatting in the Wildcited by 152
  16. 2018LF-Net: Learning Local Features from Imagescited by 151
  17. 2019Learning Two-View Correspondences and Geometry Using Order-Aware Networkcited by 149
  18. 2019SOSNet: Second Order Similarity Regularization for Local Descriptor Learningcited by 131
  19. 2020ASLFeat: Learning Local Features of Accurate Shape and Localizationcited by 130
  20. 2022MatchFormer: Interleaving Attention in Transformers for Feature Matchingcited by 126
  21. 2024Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collectionscited by 117
  22. 2023OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Modelscited by 115
  23. 2018Learning a Discriminative Feature Network for Semantic Segmentationcited by 114
  24. 2024Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizercited by 73
  25. 2023Detector-Free Structure from Motioncited by 71
  26. 2024SWAG: Splatting in the Wild images with Appearance-conditioned Gaussianscited by 61
  27. 2024FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descentcited by 61
  28. 2018GeoDesc: Learning Local Descriptors by Integrating Geometry Constraintscited by 52
  29. 2019Beyond Cartesian Representations for Local Descriptorscited by 35
  30. 2024WE-GS: An In-the-wild Efficient 3D Gaussian Representation for Unconstrained Photo Collectionscited by 33
  31. 2020Multi-View Optimization of Local Feature Geometrycited by 24
  32. 2020S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matchingcited by 23
  33. 2021Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimationcited by 17
  34. 2023SACReg: Scene-Agnostic Coordinate Regression for Visual Localizationcited by 14
  35. 2023PoseMatcher: One-shot 6D Object Pose Estimation by Deep Feature Matchingcited by 12
  36. 2023Fusing Structure from Motion and Simulation-Augmented Pose Regression from Optical Flow for Challenging Indoor Environmentscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 11.

15 papers.

Sort:

  1. 2025RoMa v2: Harder Better Faster Denser Feature Matchingcited by 51
  2. 2026LoMa: Local Feature Matching Revisitedcited by 11
  3. 2025Multi-Cali Anything: Dense Feature Multi-Frame Structure-from-Motion for Large-Scale Camera Array Calibrationcited by 6
  4. 2026Marginalized Bundle Adjustment: Multi-View Camera Pose from Monocular Depth Estimatescited by 3
  5. 2026GGPT: Geometry Grounded Point Transformercited by 3
  6. 2026CRFT: Consistent-Recurrent Feature Flow Transformer for Cross-Modal Image Registrationcited by 3
  7. 2026MV-RoMa: From Pairwise Matching into Multi-View Track Reconstructioncited by 2
  8. 2026AHAP: Reconstructing Arbitrary Humans from Arbitrary Perspectives with Geometric Priorscited by 1
  9. 2025Not All Pixels Are Equal: Confidence-Guided Attention for Feature Matchingcited by 0
  10. 2025Robust Multi-view Camera Calibration from Dense Matchescited by 0
  11. 2026PCM-NeRF: Probabilistic Camera Modeling for Neural Radiance Fields under Pose Uncertaintycited by 0
  12. 2026Fast 3D Foundation Model Initialized Gaussian Splattingcited by 0
3 more
  1. 2026DGSfM: Depth-Guided Scale-Aware Global Structure-from-Motioncited by 0
  2. 2026Robust structure from motion for aerial-ground images via detector-free feature matching and multi-view track refinementcited by 0
  3. 2026RoMa-Omega: What Feed-Forward 3D Models Know About Image Matchingcited by 0