# Human Pose-Constrained UV Map Estimation

arXiv: https://arxiv.org/abs/2501.08815 · HTML: https://mlsanity.com/paper/2501.08815/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 15 Jan 2025.

## Builds on (most cited first, 22 of 22)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [DensePose: Dense Human Pose Estimation In The Wild](https://mlsanity.com/paper/1802.00434/) (2018)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [3D Menagerie: Modeling the 3D shape and pose of animals](https://mlsanity.com/paper/1611.07700/) (2016)
- [CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark](https://mlsanity.com/paper/1812.00324/) (2018)
- [Whole-Body Human Pose Estimation in the Wild](https://mlsanity.com/paper/2007.11858/) (2020)
- [Tex2Shape: Detailed Full Human Body Geometry From a Single Image](https://mlsanity.com/paper/1904.08645/) (2019)
- [PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model](https://mlsanity.com/paper/1803.08225/) (2018)
- [Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression](https://mlsanity.com/paper/2104.02300/) (2021)
- [Pose2Seg: Detection Free Human Instance Segmentation](https://mlsanity.com/paper/1803.10683/) (2018)
- [Continuous Surface Embeddings](https://mlsanity.com/paper/2011.12438/) (2020)
- [RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation](https://mlsanity.com/paper/2312.07526/) (2023)
- [DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild](https://mlsanity.com/paper/1803.02188/) (2018)
- [Slim DensePose: Thrifty Learning from Sparse Annotations and Motion Cues](https://mlsanity.com/paper/1906.05706/) (2019)
- [Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity](https://mlsanity.com/paper/2306.07879/) (2023)
- [HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences](https://mlsanity.com/paper/2103.15573/) (2021)
- [BodyMap: Learning Full-Body Dense Correspondence Map](https://mlsanity.com/paper/2205.09111/) (2022)
- [MeshPose: Unifying DensePose and 3D Body Mesh reconstruction](https://mlsanity.com/paper/2406.10180/) (2024)
- [The Influence of Faulty Labels in Data Sets on Human Pose Estimation](https://mlsanity.com/paper/2409.03887/) (2024)

## 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.