On Coordinate Decoding for Keypoint Estimation Tasks
Not on the map. Why?
Abstract (arXiv)
A series of 2D (and 3D) keypoint estimation tasks are built upon heatmap coordinate representation, i.e. a probability map that allows for learnable and spatially aware encoding and decoding of keypoint coordinates on grids, even allowing for sub-pixel coordinate accuracy. In this report, we aim to reproduce the findings of DARK that investigated the 2D heatmap representation by highlighting the importance of the encoding of the ground truth heatmap and the decoding of the predicted heatmap to keypoint coordinates. The authors claim that a) a more principled distribution-aware coordinate decoding method overcomes the limitations of the standard techniques widely used in the literature, and b), that the reconstruction of heatmaps from ground-truth coordinates by generating accurate and continuous heatmap distributions lead to unbiased model training, contrary to the standard coordinate encoding process that quantizes the keypoint coordinates on the resolution of the input image grid.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 6 of its 8 references that are in the map. First posted on arXiv 19 Oct 2021.
Builds on
6 of 8 references.
References · 6
- 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
- 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
- 2017Integral Human Pose Regressioncited by 256
- 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
- 2018Numerical Coordinate Regression with Convolutional Neural Networkscited by 72
- 2021HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Mediacited by 29
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Detecting Pose Estimation Failures via Keypoint Self-Consistency
- 2021Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation
- 2025KeyPointDiffuser: Unsupervised 3D Keypoint Learning via Latent Diffusion Models
- 2023Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation
- 2025DaD: Distilled Reinforcement Learning for Diverse Keypoint Detection
- 2023Lightweight Super-Resolution Head for Human Pose Estimation
- 2026Learning Point Cloud Geometry as a Statistical Manifold: Theory and Practice ↗
- 2024Grid-augmented vision: A simple yet effective approach for enhanced spatial understanding in multi-modal agents