mlsanityData to 7 Oct 2026

Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation

arXiv 1906.03525 ↗First posted 8 Jun 2019cs.CVcited by 141

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a novel Pattern-Affinitive Propagation (PAP) framework to jointly predict depth, surface normal and semantic segmentation. The motivation behind it comes from the statistic observation that pattern-affinitive pairs recur much frequently across different tasks as well as within a task. Thus, we can conduct two types of propagations, cross-task propagation and task-specific propagation, to adaptively diffuse those similar patterns. The former integrates cross-task affinity patterns to adapt to each task therein through the calculation on non-local relationships. Next the latter performs an iterative diffusion in the feature space so that the cross-task affinity patterns can be widely-spread within the task. Accordingly, the learning of each task can be regularized and boosted by the complementary task-level affinities. Extensive experiments demonstrate the effectiveness and the superiority of our method on the joint three tasks. Meanwhile, we achieve the state-of-the-art or competitive results on the three related datasets, NYUD-v2, SUN-RGBD and KITTI.

Key facts. Cited by 141 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 39; 2022: 21; 2023: 30; 2024: 24; 2025: 19; 2026: 8.

141 papers.

Sort:

By area:

  1. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  2. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 283
  3. 2022CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformerscited by 229
  4. 2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 155
  5. 2024StableNormal: Reducing Diffusion Variance for Stable and Sharp Normalcited by 153
  6. 2022NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimationcited by 151
  7. 2021Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimationcited by 116
  8. 2021Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Mergingcited by 104
  9. 2022M3ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-designcited by 97
  10. 2025Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridgingcited by 95
  11. 2022InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understandingcited by 89
  12. 2023DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimationcited by 81
38 more
  1. 2021Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimationcited by 80
  2. 2021RigNet: Repetitive Image Guided Network for Depth Completioncited by 80
  3. 2021Exploring Relational Context for Multi-Task Dense Predictioncited by 71
  4. 2023iDisc: Internal Discretization for Monocular Depth Estimationcited by 71
  5. 2021Ground-aware Monocular 3D Object Detection for Autonomous Drivingcited by 65
  6. 2021InverseForm: A Loss Function for Structured Boundary-Aware Segmentationcited by 65
  7. 2024Multi-Task Dense Prediction via Mixture of Low-Rank Expertscited by 58
  8. 2021Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Darkcited by 57
  9. 2021Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimationcited by 55
  10. 2021Shape from Polarization for Complex Scenes in the Wildcited by 53
  11. 2023All in Tokens: Unifying Output Space of Visual Tasks via Soft Tokencited by 52
  12. 20213D-to-2D Distillation for Indoor Scene Parsingcited by 47
  13. 2023TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Expertscited by 45
  14. 2021Adaptive Surface Normal Constraint for Depth Estimationcited by 43
  15. 2021Learning Multiple Dense Prediction Tasks from Partially Annotated Datacited by 42
  16. 2021Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completioncited by 39
  17. 2022RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimationcited by 36
  18. 2021Single Image Depth Estimation: An Overviewcited by 35
  19. 2022Multi-Task Learning with Multi-Query Transformer for Dense Predictioncited by 34
  20. 2021Learning to Relate Depth and Semantics for Unsupervised Domain Adaptationcited by 32
  21. 2021Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image Translationcited by 31
  22. 2023SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detectioncited by 30
  23. 2025DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentationcited by 30
  24. 2022MGNet: Monocular Geometric Scene Understanding for Autonomous Drivingcited by 27
  25. 2022DesNet: Decomposed Scale-Consistent Network for Unsupervised Depth Completioncited by 27
  26. 2023DeMT: Deformable Mixer Transformer for Multi-Task Learning of Dense Predictioncited by 27
  27. 2022DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learningcited by 25
  28. 2022Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completioncited by 23
  29. 2023Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Expertscited by 23
  30. 2021Semi-supervised Multi-task Learning for Semantics and Depthcited by 22
  31. 2023InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understandingcited by 22
  32. 2024MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoderscited by 22
  33. 2022Transformers in Self-Supervised Monocular Depth Estimation with Unknown Camera Intrinsicscited by 19
  34. 2023PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentationcited by 19
  35. 2023Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Samplingcited by 19
  36. 2024Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusioncited by 19
  37. 2021Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object Segmentationcited by 18
  38. 2023Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitivescited by 18

50 most cited of 141 All 141 (JSON)