mlsanityData to 7 Oct 2026

Neural Disparity Refinement for Arbitrary Resolution Stereo

arXiv 2110.15367 ↗First posted 28 Oct 2021cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

We introduce a novel architecture for neural disparity refinement aimed at facilitating deployment of 3D computer vision on cheap and widespread consumer devices, such as mobile phones. Our approach relies on a continuous formulation that enables to estimate a refined disparity map at any arbitrary output resolution. Thereby, it can handle effectively the unbalanced camera setup typical of nowadays mobile phones, which feature both high and low resolution RGB sensors within the same device. Moreover, our neural network can process seamlessly the output of a variety of stereo methods and, by refining the disparity maps computed by a traditional matching algorithm like SGM, it can achieve unpaired zero-shot generalization performance compared to state-of-the-art end-to-end stereo models.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 39 of its 65 references that are in the map. First posted on arXiv 28 Oct 2021.

Builds on

39 of 65 references.

References · 39

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  4. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  6. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  7. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  8. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  9. 2020Convolutional Occupancy Networkscited by 760
  10. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  11. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  12. 2018Pyramid Stereo Matching Networkcited by 486
27 more
  1. 2019PointRend: Image Segmentation as Renderingcited by 439
  2. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 359
  3. 2019GA-Net: Guided Aggregation Net for End-to-end Stereo Matchingcited by 242
  4. 2020AANet: Adaptive Aggregation Network for Efficient Stereo Matchingcited by 202
  5. 2020Hierarchical Neural Architecture Search for Deep Stereo Matchingcited by 166
  6. 2015Stereo Matching by Training a Convolutional Neural Network to Compare Image Patchescited by 151
  7. 2019Hierarchical Deep Stereo Matching on High-resolution Imagescited by 126
  8. 2020HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matchingcited by 120
  9. 2021SMD-Nets: Stereo Mixture Density Networkscited by 118
  10. 2019Domain-invariant Stereo Matching Networkscited by 108
  11. 2018SegStereo: Exploiting Semantic Information for Disparity Estimationcited by 88
  12. 2018Real-time self-adaptive deep stereocited by 80
  13. 2018Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimationcited by 69
  14. 2017Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matchingcited by 63
  15. 2019Learning to Adapt for Stereocited by 42
  16. 2019SENSE: a Shared Encoder Network for Scene-flow Estimationcited by 38
  17. 2020Reversing the cycle: self-supervised deep stereo through enhanced monocular distillationcited by 34
  18. 2018EdgeStereo: A Context Integrated Residual Pyramid Network for Stereo Matchingcited by 32
  19. 2020Matching-space Stereo Networks for Cross-domain Generalizationcited by 32
  20. 2019Unsupervised Domain Adaptation for Depth Prediction from Imagescited by 29
  21. 2019Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondencecited by 23
  22. 2019Real-Time Semantic Stereo Matchingcited by 23
  23. 2020Continual Adaptation for Deep Stereocited by 23
  24. 2021On the confidence of stereo matching in a deep-learning era: a quantitative evaluationcited by 23
  25. 2019Learning End-To-End Scene Flow by Distilling Single Tasks Knowledgecited by 16
  26. 2018Left-Right Comparative Recurrent Model for Stereo Matchingcited by 12
  27. 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: 3; 2023: 5; 2024: 6; 2025: 1; 2026: 5.

20 papers.

Sort:

  1. 2023WonderJourney: Going from Anywhere to Everywherecited by 157
  2. 2022Open Challenges in Deep Stereo: the Booster Datasetcited by 48
  3. 2023NeRF-Supervised Deep Stereocited by 46
  4. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 45
  5. 2022GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Featurecited by 43
  6. 2023Booster: a Benchmark for Depth from Images of Specular and Transparent Surfacescited by 33
  7. 2026LoGeR: Long-Context Geometric Reconstruction with Hybrid Memorycited by 33
  8. 2024A Survey on Deep Stereo Matching in the Twentiescited by 23
  9. 2023Revisiting Depth Completion from a Stereo Matching Perspective for Cross-domain Generalizationcited by 18
  10. 2024Federated Online Adaptation for Deep Stereocited by 12
  11. 2023Active Stereo Without Pattern Projectorcited by 8
  12. 2024Cross-spectral Gated-RGB Stereo Depth Estimationcited by 8
8 more
  1. 2022RGB-Multispectral Matching: Dataset, Learning Methodology, Evaluationcited by 6
  2. 2024Self-Assessed Generation: Trustworthy Label Generation for Optical Flow and Stereo Matching in Real-worldcited by 3
  3. 2025NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfacescited by 3
  4. 2026TrajVG: 3D Trajectory-Coupled Visual Geometry Learningcited by 3
  5. 2024Active Stereo in the Wild through Virtual Pattern Projectioncited by 0
  6. 2026EventHub: Data Factory for Generalizable Event-Based Stereo Networks without Active Sensorscited by 0
  7. 2026Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereocited by 0
  8. 2026ProDyGS: Dynamic Gaussian Splatting from a Single Static Monocular Cameracited by 0