mlsanityData to 14 Oct 2026

Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces

arXiv 2301.08245 ↗First posted 19 Jan 2023cs.CVcited by 33

Not on the map. Why?

Abstract (arXiv)

Estimating depth from images nowadays yields outstanding results, both in terms of in-domain accuracy and generalization. However, we identify two main challenges that remain open in this field: dealing with non-Lambertian materials and effectively processing high-resolution images. Purposely, we propose a novel dataset that includes accurate and dense ground-truth labels at high resolution, featuring scenes containing several specular and transparent surfaces. Our acquisition pipeline leverages a novel deep space-time stereo framework, enabling easy and accurate labeling with sub-pixel precision. The dataset is composed of 606 samples collected in 85 different scenes, each sample includes both a high-resolution pair (12 Mpx) as well as an unbalanced stereo pair (Left: 12 Mpx, Right: 1.1 Mpx), typical of modern mobile devices that mount sensors with different resolutions. Additionally, we provide manually annotated material segmentation masks and 15K unlabeled samples. The dataset is composed of a train set and two test sets, the latter devoted to the evaluation of stereo and monocular depth estimation networks. Our experiments highlight the open challenges and future research directions in this field.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). Builds on 52 of its 98 references that are in the map. First posted on arXiv 19 Jan 2023.

Builds on

52 of 98 references.

References · 52

  1. 2021Vision Transformers for Dense Predictioncited by 1,803
  2. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  3. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  4. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 881
  5. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  6. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  7. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 732
  8. 2018Taskonomy: Disentangling Task Transfer Learningcited by 634
  9. 2018Pyramid Stereo Matching Networkcited by 489
  10. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 403
  11. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 360
  12. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 353
38 more
  1. 2017Sparsity Invariant CNNscited by 326
  2. 2021DSEC: A Stereo Event Camera Dataset for Driving Scenarioscited by 303
  3. 2019GA-Net: Guided Aggregation Net for End-to-end Stereo Matchingcited by 244
  4. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 216
  5. 2022Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlationcited by 197
  6. 2018The ApolloScape Open Dataset for Autonomous Driving and its Applicationcited by 190
  7. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  8. 2016Single-Image Depth Perception in the Wildcited by 180
  9. 2020Hierarchical Neural Architecture Search for Deep Stereo Matchingcited by 166
  10. 2021CFNet: Cascade and Fused Cost Volume for Robust Stereo Matchingcited by 154
  11. 2015Stereo Matching by Training a Convolutional Neural Network to Compare Image Patchescited by 151
  12. 2019Self-Supervised Monocular Depth Hintscited by 127
  13. 2019Hierarchical Deep Stereo Matching on High-resolution Imagescited by 126
  14. 2021SMD-Nets: Stereo Mixture Density Networkscited by 120
  15. 2020Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volumecited by 116
  16. 2019Domain-invariant Stereo Matching Networkscited by 109
  17. 2021Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Mergingcited by 104
  18. 2018SegStereo: Exploiting Semantic Information for Disparity Estimationcited by 88
  19. 2018Real-time self-adaptive deep stereocited by 80
  20. 2020Monocular Depth Estimation Based On Deep Learning: An Overviewcited by 68
  21. 2018Learning Monocular Depth by Distilling Cross-domain Stereo Networkscited by 64
  22. 2019Learning monocular depth estimation infusing traditional stereo knowledgecited by 64
  23. 2017Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matchingcited by 63
  24. 2020OASIS: A Large-Scale Dataset for Single Image 3D in the Wildcited by 62
  25. 2020Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumescited by 50
  26. 2022Open Challenges in Deep Stereo: the Booster Datasetcited by 48
  27. 2022GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Featurecited by 43
  28. 2020Predicting Sharp and Accurate Occlusion Boundaries in Monocular Depth Estimation Using Displacement Fieldscited by 40
  29. 2020Distilled Semantics for Comprehensive Scene Understanding from Videoscited by 39
  30. 2022ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networkscited by 39
  31. 2019Monocular Depth Estimation: A Surveycited by 38
  32. 2020Reversing the cycle: self-supervised deep stereo through enhanced monocular distillationcited by 34
  33. 2018EdgeStereo: A Context Integrated Residual Pyramid Network for Stereo Matchingcited by 32
  34. 2020Matching-space Stereo Networks for Cross-domain Generalizationcited by 32
  35. 2019Unsupervised Domain Adaptation for Depth Prediction from Imagescited by 29
  36. 2019Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondencecited by 23
  37. 2019Real-Time Semantic Stereo Matchingcited by 23
  38. 2020Continual Adaptation for Deep Stereocited by 23

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 9; 2025: 16; 2026: 8.

33 papers.

Sort:

By area:

  1. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 404
  2. 2025FoundationStereo: Zero-Shot Stereo Matchingcited by 173
  3. 2025UniDepthV2: Universal Monocular Metric Depth Estimation Made Simplercited by 173
  4. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 47
  5. 2024Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditionscited by 29
  6. 2025Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matchingcited by 28
  7. 2024A Survey on Deep Stereo Matching in the Twentiescited by 23
  8. 2024SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillationcited by 21
  9. 2025Sharp Monocular View Synthesis in Less Than a Secondcited by 20
  10. 2024The Third Monocular Depth Estimation Challengecited by 10
  11. 2026MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sourcescited by 10
  12. 2024Towards Robust Monocular Depth Estimation in Non-Lambertian Surfacescited by 9
21 more
  1. 2024SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimationcited by 8
  2. 2025The Fourth Monocular Depth Estimation Challengecited by 8
  3. 2025What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?cited by 7
  4. 2025XYZ-IBD: Benchmarking Robust 6D Object Pose Estimation under Real-World Industrial Complexitycited by 7
  5. 2025Towards Open-World Generation of Stereo Images and Unsupervised Matchingcited by 6
  6. 2025NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfacescited by 3
  7. 2026WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matchingcited by 3
  8. 2025One Look is Enough: Seamless Patchwise Refinement for Zero-Shot Monocular Depth Estimation on High-Resolution Imagescited by 2
  9. 2025PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Modelscited by 2
  10. 2026SeeClear: Reliable Transparent Object Depth Estimation via Generative Opacificationcited by 2
  11. 2025ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Drivingcited by 1
  12. 2025EGSA-PT:Edge-Guided Spatial Attention with Progressive Training for Monocular Depth Estimation and Segmentation of Transparent Objectscited by 1
  13. 2026Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attentioncited by 1
  14. 2024Active Stereo in the Wild through Virtual Pattern Projectioncited by 0
  15. 2025Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfacescited by 0
  16. 2025GeoDiff: Geometry-Guided Diffusion for Metric Depth Estimationcited by 0
  17. 2025The 3D Mirage: Probing and Taming 3D Hallucinationscited by 0
  18. 2026WAVE-Stereo: Warp-Aligned Volume Encoding for Stereo Matchingcited by 0
  19. 2026GIFT: Geometry-Invariant Fine-Tuning for Non-Lambertian Monocular Depth Estimationcited by 0
  20. 2026NBS: No Bias Stereocited by 0
  21. 2026Spackle: Completing Large View Single Image NVS with Adaptive Gaussianscited by 0