mlsanityData to 7 Oct 2026

NBS: No Bias Stereo

arXiv 2608.28933 ↗First posted 28 Aug 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Stereo reconstruction is one of the last remaining Computer Vision tasks where all state-of-the-art methods employ a heavy architectural inductive bias. Even though it has been demonstrated that the task can be solved using general-purpose methods, it is widely believed that inductive biases in stereo are strictly necessary for both high-quality results and computational efficiency. We challenge this paradigm. In this paper, we demonstrate that both state-of-the-art accuracy and superior runtime efficiency are achievable with a model completely devoid of architectural inductive biases, relying instead on a simple, end-to-end Vision Transformer. By training on massive synthetic datasets, we show that pure data-driven learning can surpass explicitly engineered geometry. This work proves that explicit inductive biases are no longer a prerequisite for stereo matching, ultimately unlocking true scaling laws for continuous improvement in 3D reconstruction.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 52 of its 67 references that are in the map. First posted on arXiv 28 Aug 2026.

Builds on

52 of 67 references.

References · 52

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  3. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  4. 2021Vision Transformers for Dense Predictioncited by 1,789
  5. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  6. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  7. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  8. 2024Depth Anything V2cited by 1,385
  9. 2025DINOv3cited by 1,297
  10. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  11. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  12. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
38 more
  1. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 494
  2. 2018Pyramid Stereo Matching Networkcited by 486
  3. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  4. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  5. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 359
  6. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 356
  7. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 348
  8. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 290
  9. 2022Unifying Flow, Stereo and Depth Estimationcited by 270
  10. 2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Detailscited by 250
  11. 2020AANet: Adaptive Aggregation Network for Efficient Stereo Matchingcited by 202
  12. 2022Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlationcited by 197
  13. 2020Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformerscited by 190
  14. 2023Iterative Geometry Encoding Volume for Stereo Matchingcited by 188
  15. 2023Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereocited by 170
  16. 2025FoundationStereo: Zero-Shot Stereo Matchingcited by 168
  17. 2022CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flowcited by 165
  18. 2021CFNet: Cascade and Fused Cost Volume for Robust Stereo Matchingcited by 153
  19. 2021SMD-Nets: Stereo Mixture Density Networkscited by 118
  20. 2019DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatchcited by 114
  21. 2024Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matchingcited by 98
  22. 2018Falling Things: A Synthetic Dataset for 3D Object Detection and Pose Estimationcited by 92
  23. 2020PCW-Net: Pyramid Combination and Warping Cost Volume for Stereo Matchingcited by 62
  24. 2022Accurate and Efficient Stereo Matching via Attention Concatenation Volumecited by 59
  25. 2024IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matchingcited by 55
  26. 2025DEFOM-Stereo: Depth Foundation Model Based Stereo Matchingcited by 51
  27. 2024MoCha-Stereo: Motif Channel Attention Network for Stereo Matchingcited by 48
  28. 2021Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitationcited by 47
  29. 2021Bilateral Grid Learning for Stereo Matching Networkscited by 46
  30. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 45
  31. 2022Context-Enhanced Stereo Transformercited by 37
  32. 2025TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigationcited by 35
  33. 2023Booster: a Benchmark for Depth from Images of Specular and Transparent Surfacescited by 33
  34. 2025Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matchingcited by 23
  35. 2024All-in-One: Transferring Vision Foundation Models into Stereo Matchingcited by 16
  36. 2024Match Stereo Videos via Bidirectional Alignmentcited by 11
  37. 2025What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?cited by 7
  38. 2024UniTT-Stereo: Unified Training of Transformer for Enhanced Stereo Matchingcited by 3

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.