mlsanityData to 7 Oct 2026

Open Challenges in Deep Stereo: the Booster Dataset

arXiv 2206.04671 ↗First posted 9 Jun 2022cs.CVcited by 48

Not on the map. Why?

Abstract (arXiv)

We present a novel high-resolution and challenging stereo dataset framing indoor scenes annotated with dense and accurate ground-truth disparities. Peculiar to our dataset is the presence of several specular and transparent surfaces, i.e. the main causes of failures for state-of-the-art stereo networks. Our acquisition pipeline leverages a novel deep space-time stereo framework which allows for easy and accurate labeling with sub-pixel precision. We release a total of 419 samples collected in 64 different scenes and annotated with dense ground-truth disparities. Each sample include a high-resolution pair (12 Mpx) as well as an unbalanced pair (Left: 12 Mpx, Right: 1.1 Mpx). Additionally, we provide manually annotated material segmentation masks and 15K unlabeled samples. We evaluate state-of-the-art deep networks based on our dataset, highlighting their limitations in addressing the open challenges in stereo and drawing hints for future research.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 27 of its 58 references that are in the map. First posted on arXiv 9 Jun 2022.

Builds on

27 of 58 references.

References · 27

  1. 2021Vision Transformers for Dense Predictioncited by 1,789
  2. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  3. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  4. 2018Pyramid Stereo Matching Networkcited by 486
  5. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 359
  6. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 348
  7. 2021DSEC: A Stereo Event Camera Dataset for Driving Scenarioscited by 297
  8. 2019GA-Net: Guided Aggregation Net for End-to-end Stereo Matchingcited by 242
  9. 2018The ApolloScape Open Dataset for Autonomous Driving and its Applicationcited by 188
  10. 2020Hierarchical Neural Architecture Search for Deep Stereo Matchingcited by 166
  11. 2021CFNet: Cascade and Fused Cost Volume for Robust Stereo Matchingcited by 153
  12. 2015Stereo Matching by Training a Convolutional Neural Network to Compare Image Patchescited by 151
15 more
  1. 2019Hierarchical Deep Stereo Matching on High-resolution Imagescited by 126
  2. 2021SMD-Nets: Stereo Mixture Density Networkscited by 118
  3. 2019Domain-invariant Stereo Matching Networkscited by 108
  4. 2018SegStereo: Exploiting Semantic Information for Disparity Estimationcited by 88
  5. 2018Real-time self-adaptive deep stereocited by 80
  6. 2017Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matchingcited by 63
  7. 2020Reversing the cycle: self-supervised deep stereo through enhanced monocular distillationcited by 34
  8. 2018EdgeStereo: A Context Integrated Residual Pyramid Network for Stereo Matchingcited by 32
  9. 2020Matching-space Stereo Networks for Cross-domain Generalizationcited by 32
  10. 2019Unsupervised Domain Adaptation for Depth Prediction from Imagescited by 29
  11. 2019Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondencecited by 23
  12. 2019Real-Time Semantic Stereo Matchingcited by 23
  13. 2020Continual Adaptation for Deep Stereocited by 23
  14. 2021Neural Disparity Refinement for Arbitrary Resolution Stereocited by 20
  15. 2016Detect, Replace, Refine: Deep Structured Prediction For Pixel Wise Labelingcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 12; 2025: 18; 2026: 14.

48 papers.

Sort:

By area:

  1. 2024Depth Anything V2cited by 1,385
  2. 2022CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flowcited by 165
  3. 2025DEFOM-Stereo: Depth Foundation Model Based Stereo Matchingcited by 51
  4. 2023NeRF-Supervised Deep Stereocited by 46
  5. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 45
  6. 2023Learning Depth Estimation for Transparent and Mirror Surfacescited by 34
  7. 2023Booster: a Benchmark for Depth from Images of Specular and Transparent Surfacescited by 33
  8. 2024Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditionscited by 29
  9. 2026Masked Depth Modeling for Spatial Perceptioncited by 24
  10. 2024A Survey on Deep Stereo Matching in the Twentiescited by 23
  11. 2025MonSter++: Unified Stereo Matching, Multi-view Stereo, and Real-time Stereo with Monodepth Priorscited by 19
  12. 2024Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesiscited by 18
36 more
  1. 2024Robust Synthetic-to-Real Transfer for Stereo Matchingcited by 15
  2. 2025BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignmentcited by 15
  3. 2024LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-Layer Optical Flowcited by 11
  4. 2024The Third Monocular Depth Estimation Challengecited by 10
  5. 2025Diving into the Fusion of Monocular Priors for Generalized Stereo Matchingcited by 10
  6. 2024Towards Robust Monocular Depth Estimation in Non-Lambertian Surfacescited by 9
  7. 2024SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimationcited by 8
  8. 2025Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimationcited by 8
  9. 2025The Fourth Monocular Depth Estimation Challengecited by 8
  10. 2025StereoAdapter: Adapting Stereo Depth Estimation to Underwater Scenescited by 8
  11. 2026PromptStereo: Zero-Shot Stereo Matching via Structure and Motion Promptscited by 5
  12. 2026PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimationcited by 5
  13. 2024UniTT-Stereo: Unified Training of Transformer for Enhanced Stereo Matchingcited by 3
  14. 20253D Visual Illusion Depth Estimationcited by 3
  15. 2025Multi-Label Stereo Matching for Transparent Scene Depth Estimationcited by 3
  16. 2025NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfacescited by 3
  17. 2025DepthFocus: Controllable Depth Estimation for See-Through Scenescited by 3
  18. 2025PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Modelscited by 2
  19. 2025RoSe: Robust Self-supervised Stereo Matching under Adverse Weather Conditionscited by 2
  20. 2025FastViDAR: Real-Time Omnidirectional Depth Estimation via Alternative Hierarchical Attentioncited by 2
  21. 2025StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Spacecited by 2
  22. 2024MaDis-Stereo: Enhanced Stereo Matching via Distilled Masked Image Modelingcited by 1
  23. 2025ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Drivingcited by 1
  24. 2025EGSA-PT:Edge-Guided Spatial Attention with Progressive Training for Monocular Depth Estimation and Segmentation of Transparent Objectscited by 1
  25. 2026SMFormer: Empowering Self-supervised Stereo Matching via Foundation Models and Data Augmentationcited by 1
  26. 2026WideDepth: Millimeter-Accurate Benchmark for Fisheye Depth Estimationcited by 1
  27. 2026Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimationcited by 1
  28. 2026Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attentioncited by 1
  29. 2025DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patchescited by 0
  30. 2026Any Resolution Any Geometry: From Multi-View To Multi-Patchcited by 0
  31. 2026Geometry Reinforced Efficient Attention Tuning Equipped with Normals for Robust Stereo Matchingcited by 0
  32. 2026SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Groupingcited by 0
  33. 2026LinStereo: Linear-Complexity Global Attention for Multi-Scale Iterative Stereo Matchingcited by 0
  34. 2026Geometric Distillation from Rectified Stereo: Leveraging Epipolar Cues for Monocular Depthcited by 0
  35. 2026Beyond Visual Ambiguity: Guiding Robust Monocular Depth Estimation in Challenging Scenarios via Detailed Long Captionscited by 0
  36. 2026DepthEvidence: Unifying Metric Depth Prediction and Geometric Reasoning in Multimodal Language Modelscited by 0