1 Repo
Algorithms designed to improve the precision of spatial coordinate representation and recovery in neural networks.
Distinct from Coordinate-Based Neural Representations: The candidates focus on neural representations or general optimizers, not the precision of coordinate encoding/decoding.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Coordinate Encoding Optimizations. Refine with filters or upvote what's useful.
MMPose is a PyTorch-based pose estimation toolbox and deep learning training pipeline designed for detecting 2D and 3D keypoints on humans, animals, and faces. It serves as a computer vision model zoo and a framework for both 2D pose estimation and 3D pose lifting. The project is distinguished by its modular architecture and extensibility, employing a registry-based system and hierarchical configurations to allow for custom algorithm integration and model pipeline customization. It supports diverse estimation paradigms, including top-down, bottom-up, and two-stage pose lifting workflows. The
Implements unbiased encoding and decoding algorithms to improve the precision of keypoint localization.