PinataFarms/DAD-3DHeads
Official repo for DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image (CVPR 2022).
This project helps researchers and developers working with computer vision tasks to accurately reconstruct 3D head models from single 2D images. It provides a dataset of diverse head images with detailed 3D annotations, which serves as input, and outputs various visualizations like 2D/3D landmarks, face/head meshes, and head pose. This is used by computer vision scientists, researchers, and developers building applications related to 3D facial analysis or avatar creation.
495 stars.
Use this if you need a high-quality, diverse dataset and benchmark for training and evaluating models that convert single images into precise 3D head reconstructions or need tools to visualize 3D head models from images.
Not ideal if you are looking for a ready-to-use application for end-users rather than a research dataset and development tools for building such applications.
Stars
495
Forks
44
Language
Python
License
—
Category
Last pushed
Jan 23, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/PinataFarms/DAD-3DHeads"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
DeepLabCut/DeepLabCut
Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with...
openpifpaf/openpifpaf
Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and...
lambdaloop/anipose
🐜🐀🐒🚶 A toolkit for robust markerless 3D pose estimation
DIYer22/bpycv
Computer vision utils for Blender (generate instance annoatation, depth and 6D pose by one line code)
NeLy-EPFL/DeepFly3D
Motion capture (markerless 3D pose estimation) pipeline and helper GUI for tethered Drosophila.