mlsanityData to 7 Oct 2026

Human Pose-Constrained UV Map Estimation

arXiv 2501.08815 ↗First posted 15 Jan 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

UV map estimation is used in computer vision for detailed analysis of human posture or activity. Previous methods assign pixels to body model vertices by comparing pixel descriptors independently, without enforcing global coherence or plausibility in the UV map. We propose Pose-Constrained Continuous Surface Embeddings (PC-CSE), which integrates estimated 2D human pose into the pixel-to-vertex assignment process. The pose provides global anatomical constraints, ensuring that UV maps remain coherent while preserving local precision. Evaluation on DensePose COCO demonstrates consistent improvement, regardless of the chosen 2D human pose model. Whole-body poses offer better constraints by incorporating additional details about the hands and feet. Conditioning UV maps with human pose reduces invalid mappings and enhances anatomical plausibility. In addition, we highlight inconsistencies in the ground-truth annotations.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 37 references that are in the map. First posted on arXiv 15 Jan 2025.

Builds on

22 of 37 references.

References · 22

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2017Mask R-CNNcited by 7,259
  3. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  4. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  5. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
  6. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  7. 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 310
  8. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  9. 2020Whole-Body Human Pose Estimation in the Wildcited by 178
  10. 2019Tex2Shape: Detailed Full Human Body Geometry From a Single Imagecited by 166
  11. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  12. 2021Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regressioncited by 112
10 more
  1. 2018Pose2Seg: Detection Free Human Instance Segmentationcited by 107
  2. 2020Continuous Surface Embeddingscited by 79
  3. 2023RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimationcited by 33
  4. 2018DenseReg: Fully Convolutional Dense Shape Regression In-the-Wildcited by 32
  5. 2019Slim DensePose: Thrifty Learning from Sparse Annotations and Motion Cuescited by 13
  6. 2023Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguitycited by 13
  7. 2021HumanGPS: Geodesic PreServing Feature for Dense Human Correspondencescited by 12
  8. 2022BodyMap: Learning Full-Body Dense Correspondence Mapcited by 11
  9. 2024MeshPose: Unifying DensePose and 3D Body Mesh reconstructioncited by 8
  10. 2024The Influence of Faulty Labels in Data Sets on Human Pose Estimationcited by 2

Built on by

Not cited yet.