mlsanityData to 14 Oct 2026

Geometric Constraints in Deep Learning Frameworks: A Survey

arXiv 2403.12431 ↗First posted 19 Mar 2024cs.CV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Stereophotogrammetry is an established technique for scene understanding. Its origins go back to at least the 1800s when people first started to investigate using photographs to measure the physical properties of the world. Since then, thousands of approaches have been explored. The classic geometric technique of Shape from Stereo is built on using geometry to define constraints on scene and camera deep learning without any attempt to explicitly model the geometry. In this survey, we explore geometry-inspired deep learning-based frameworks. We compare and contrast geometry enforcing constraints integrated into deep learning frameworks for depth estimation and other closely related vision tasks. We present a new taxonomy for prevalent geometry enforcing constraints used in modern deep learning frameworks. We also present insightful observations and potential future research directions.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 60 of its 108 references that are in the map. First posted on arXiv 19 Mar 2024.

Builds on

60 of 108 references.

References · 60

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  6. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  7. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  8. 2023RWKV: Reinventing RNNs for the Transformer Eracited by 827
  9. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  10. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  11. 2016Direct Sparse Odometrycited by 485
  12. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
38 more
  1. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 417
  2. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  3. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 360
  4. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 342
  5. 2018DeepMVS: Learning Multi-view Stereopsiscited by 277
  6. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 254
  7. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 234
  8. 2017UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Losscited by 202
  9. 2018Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraintscited by 179
  10. 2019Cost Volume Pyramid Based Depth Inference for Multi-View Stereocited by 154
  11. 2019Point-Based Multi-View Stereo Networkcited by 147
  12. 2018Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundariescited by 145
  13. 2019Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Cameracited by 130
  14. 2020Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimationcited by 120
  15. 2021TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformerscited by 117
  16. 2017SegFlow: Joint Learning for Video Object Segmentation and Optical Flowcited by 92
  17. 2018SegStereo: Exploiting Semantic Information for Disparity Estimationcited by 88
  18. 2018Deep Feature Factorization For Concept Discoverycited by 64
  19. 2020Normalized and Geometry-Aware Self-Attention Network for Image Captioningcited by 63
  20. 2019Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimationcited by 61
  21. 2019Unsupervised Monocular Depth and Ego-motion Learning with Structure and Semanticscited by 49
  22. 2019Normal Assisted Stereo Depth Estimationcited by 49
  23. 2015Loss Functions for Neural Networks for Image Processingcited by 41
  24. 2020P2Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimationcited by 41
  25. 2017Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistencycited by 40
  26. 2019Learning Unsupervised Multi-View Stereopsis via Robust Photometric Consistencycited by 40
  27. 2021Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentationcited by 31
  28. 2021Digging into Uncertainty in Self-supervised Multi-view Stereocited by 31
  29. 2019MVS^2: Deep Unsupervised Multi-view Stereo with Multi-View Symmetrycited by 30
  30. 2020M^3VSNet: Unsupervised Multi-metric Multi-view Stereo Networkcited by 29
  31. 2021Self-supervised Learning of Depth Inference for Multi-view Stereocited by 28
  32. 2021Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimationcited by 27
  33. 2021Attentive and Contrastive Learning for Joint Depth and Motion Field Estimationcited by 24
  34. 2019Real-Time Semantic Stereo Matchingcited by 23
  35. 2021Deep Learning for Multi-View Stereo via Plane Sweep: A Surveycited by 16
  36. 2021Multi-View Stereo with Transformercited by 14
  37. 2022DS-MVSNet: Unsupervised Multi-view Stereo via Depth Synthesiscited by 9
  38. 2023A geometry-aware deep network for depth estimation in monocular endoscopycited by 8

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Blending 3D Geometry and Machine Learning for Multi-View Stereopsiscited by 0