Research map / 3D vision / Human pose estimation
UltraPose: Synthesizing Dense Pose With 1 Billion Points by Human-Body Decoupling 3D Model
Haonan Yan, Jiaqi Chen, Xujie Zhang, Shengkai Zhang, Nianhong Jiao, Xiaodan Liang, Tianxiang Zheng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| scale training data from 5K to 500K synthetic images | TransUltra · UltraPose | AP: 49.1 -> 56.2 | Improved |
| scale training data from 5K to 500K synthetic images | DensePose · UltraPose | AP: 39.6 -> 46.1 | Improved |
| scale training data from 5K to 500K synthetic images | Confidence Estimation · UltraPose | AR: 41.7 -> 58.7 | Improved |
| scale training data from 5K to 500K synthetic images | DeepLabV3 Head · UltraPose | AP: 43.1 -> 52.3 | Improved |
| use TransUltra (transformer, U-Net, keypoint prior) instead of DeepLabV3 head | DeepLabV3 Head · UltraPose (500K) | AP: 52.3 -> 56.2 | Improved |
| use TransUltra instead of DeepLabV3 head with 5K data | DeepLabV3 Head · UltraPose-5K | AP: 43.1 -> 49.1 | Improved |
| use TransUltra instead of DensePose-RCNN | DensePose · UltraPose (500K) | AP@GPS50: 72.4 -> 91.8 | Improved |
| use TransUltra instead of Confidence Estimation | Confidence Estimation · UltraPose (500K) | AR@GPS75: 73.0 -> 84.7 | Improved |
| train on synthetic UltraPose with occlusion augmentation and test on DensePose-COCO | TransUltra · DensePose-COCO (qualitative) | visual quality | Improved |
Closest papers by meaning
- DensePose: Dense Human Pose Estimation in the Wild (CVPR 2018 · similarity 0.91)
- SimPose: Effectively Learning DensePose and Surface Normals of People from Simulated Data (ECCV 2020 · similarity 0.91)
- HoloPose: Holistic 3D Human Reconstruction In-The-Wild (CVPR 2019 · similarity 0.89)
- Learning 3D Human Shape and Pose from Dense Body Parts (TPAMI 2020 · similarity 0.89)
- MeshPose: Unifying DensePose and 3D Body Mesh Reconstruction (CVPR 2024 · similarity 0.88)
- PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
