Research map / 3D vision / Human pose estimation
SimCC: A Simple Coordinate Classification Perspective for Human Pose Estimation
Yanjie Li, Sen Yang, Peidong Liu, Shoukui Zhang, Yunxiao Wang, Zhicheng Wang, Wankou Yang, Shu-Tao Xia
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 |
|---|---|---|---|
| replace 2D heatmap with SimCC coordinate classification | HRNet-W48 · COCO val2017 (64x64) | AP: 48.5 -> 59.7 | Improved |
| replace 2D heatmap with SimCC coordinate classification | HRNet-W48 · COCO val2017 (256x192) | AP: 75.1 -> 75.9 | Improved |
| replace DARK post-processing with SimCC | TokenPose-S · COCO val2017 (64x64) | AP: 57.1 -> 62.8 | Improved |
| add refinement post-processing (DARK) to heatmap (ablation) | TokenPose-S · COCO val2017 (64x64) | AP: 35.9 -> 57.1 | Improved |
| remove deconvolution upsampling layers via SimCC | SimpleBaseline-R50 · COCO val2017 (256x192) | AP: 70.4 -> 70.8 | Improved |
| add deconvolution upsampling modules to SimCC (ablation) | SimpleBaseline-R50 · COCO val2017 (256x192) | AP: 70.8 -> 71.4 | Improved |
| add deconvolution upsampling modules to SimCC (ablation) | SimpleBaseline-R50 · COCO val2017 (128x128) | AP: 62.6 -> 62.6 | No clear effect |
| add deconvolution upsampling modules to SimCC (ablation) | SimpleBaseline-R50 · COCO val2017 (64x64) | AP: 39.3 -> 40.8 | Improved |
| add equal label smoothing (ablation) | SimCC SimBa-R50 · COCO val2017 (384x288) | AP: 71.3 -> 73.0 | Improved |
| use Gaussian instead of equal label smoothing (ablation) | SimCC SimBa-R50 · COCO val2017 (384x288) | AP: 73.0 -> 73.4 | Improved |
| use Laplace instead of equal label smoothing (ablation) | SimCC SimBa-R50 · COCO val2017 (384x288) | AP: 73.0 -> 73.0 | No clear effect |
| replace 2D heatmap with 1D heatmap regression | SimpleBaseline-R50 · COCO val2017 (256x256) | AP: 68.8 -> 68.5 | Hurt |
Later papers that compared with this method
2 later accepted papers report SimCC as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Continuous Heatmap Regression for Pose Estimation via Implicit Neural Representation (NeurIPS 2024 · better on 7 of 7 shared results)
- Spatial-Aware Regression for Keypoint Localization (CVPR 2024 · better on 1 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation (CVPR 2024 · similarity 0.86)
- ProbPose: A Probabilistic Approach to 2D Human Pose Estimation (CVPR 2025 · similarity 0.85)
- $\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation (NeurIPS 2024 · similarity 0.85)
- Continuous Heatmap Regression for Pose Estimation via Implicit Neural Representation (NeurIPS 2024 · similarity 0.84)
- Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation (NeurIPS 2024 · similarity 0.84)
- Optimizing Human Pose Estimation Through Focused Human and Joint Regions (AAAI 2025 · similarity 0.84)
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.
