mlsanityData to 14 Oct 2026

BBoxMaskPose v2: Expanding Mutual Conditioning to 3D

arXiv 2601.15200 ↗First posted 21 Jan 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Most 2D human pose estimation benchmarks are nearly saturated, with the exception of crowded scenes. We introduce PMPose, a top-down 2D pose estimator that incorporates the probabilistic formulation and the mask-conditioning. PMPose improves crowded pose estimation without sacrificing performance on standard scenes. Building on this, we present BBoxMaskPose v2 (BMPv2) integrating PMPose and an enhanced SAM-based mask refinement module. BMPv2 surpasses state-of-the-art by 1.5 average precision (AP) points on COCO and 6 AP points on OCHuman, becoming the first method to exceed 50 AP on OCHuman. We demonstrate that BMP's 2D prompting of 3D model improves 3D pose estimation in crowded scenes and that advances in 2D pose quality directly benefit 3D estimation. Results on the new OCHuman-Pose dataset show that multi-person performance is more affected by pose prediction accuracy than by detection. The code, models, and data are available on https://MiraPurkrabek.github.io/BBox-Mask-Pose/.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 66 of its 84 references that are in the map. First posted on arXiv 21 Jan 2026.

Builds on

66 of 84 references.

References · 66

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  5. 2022A ConvNet for the 2020scited by 3,579
  6. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  7. 2018YOLOv3: An Incremental Improvementcited by 2,659
  8. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  9. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  10. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
  11. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  12. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 929
38 more
  1. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 751
  2. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 724
  3. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  4. 2017Learning from Synthetic Humanscited by 359
  5. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  6. 2018CrowdHuman: A Benchmark for Detecting Human in a Crowdcited by 284
  7. 2022DETRs with Collaborative Hybrid Assignments Trainingcited by 274
  8. 2021Mesh Graphormercited by 265
  9. 2017Integral Human Pose Regressioncited by 256
  10. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 236
  11. 2024Sapiens: Foundation for Human Vision Modelscited by 229
  12. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  13. 2021AGORA: Avatars in Geography Optimized for Regression Analysiscited by 205
  14. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 195
  15. 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 175
  16. 2018Instance-level Human Parsing via Part Grouping Networkcited by 134
  17. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  18. 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
  19. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  20. 2017Compositional Human Pose Regressioncited by 124
  21. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
  22. 2018Pose2Seg: Detection Free Human Instance Segmentationcited by 107
  23. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  24. 2024Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shotcited by 101
  25. 2025PromptHMR: Promptable Human Mesh Recoverycited by 76
  26. 2017AI Challenger : A Large-scale Dataset for Going Deeper in Image Understandingcited by 73
  27. 2023UniHCP: A Unified Model for Human-Centric Perceptionscited by 59
  28. 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimationcited by 59
  29. 2018Parsing R-CNN for Instance-Level Human Analysiscited by 53
  30. 2017Human Pose Regression by Combining Indirect Part Detection and Contextual Informationcited by 52
  31. 2024SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentationcited by 44
  32. 2021Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimationcited by 30
  33. 2021End-to-End Trainable Multi-Instance Pose Estimation with Transformerscited by 30
  34. 2025From Skin to Skeleton: Towards Biomechanically Accurate 3D Digital Humanscited by 27
  35. 2023Hulk: A Universal Knowledge Translator for Human-Centric Taskscited by 22
  36. 2023Semantic-aware SAM for Point-Prompted Instance Segmentationcited by 16
  37. 2025OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Promptscited by 15
  38. 2023Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguitycited by 13

50 most cited of 66 All 66 (JSON)

Built on by

Not cited yet.