DeepAI AI Chat
Log In Sign Up

On Coordinate Decoding for Keypoint Estimation Tasks

by   Anargyros Chatzitofis, et al.

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.


Topology-inspired Cross-domain Network for Developmental Cervical Stenosis Quantification

Developmental Canal Stenosis (DCS) quantification is crucial in cervical...

Distribution-Aware Coordinate Representation for Human Pose Estimation

While being the de facto standard coordinate representation in human pos...

Learning Probabilistic Coordinate Fields for Robust Correspondences

We introduce Probabilistic Coordinate Fields (PCFs), a novel geometric-i...

Identifiability of Discretized Latent Coordinate Systems via Density Landmarks Detection

Disentanglement aims to recover meaningful latent ground-truth factors f...

Human 3D keypoints via spatial uncertainty modeling

We introduce a technique for 3D human keypoint estimation that directly ...

The Galactic 3D large-scale dust distribution via Gaussian process regression on spherical coordinates

Knowing the Galactic 3D dust distribution is relevant for understanding ...