NVlabs/blade

Official PyTorch implementation of BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation (CVPR 2025). BLADE tackles close-range human mesh recovery where perspective distortion is strongest, and solves for camera pose and focal length in addition to SMPL(-X) parameters.

34
/ 100
Emerging

This project helps capture precise 3D human body shapes and movements from a single camera image, even when the person is very close to the camera. It takes an image of a person and outputs a detailed 3D mesh model of their body, along with accurate information about their position and the camera's perspective. It is designed for professionals in animation, virtual reality, motion capture, or sports analysis who need accurate 3D human models from standard video.

Use this if you need highly accurate 3D human body models and poses reconstructed from single images, especially in scenarios where subjects are close to the camera, leading to significant perspective distortion.

Not ideal if your primary goal is general object detection or if you only need rough 2D pose estimations, as this tool is specifically optimized for detailed 3D human body reconstruction.

3D-motion-capture human-modeling virtual-reality-animation sports-biomechanics computer-vision
No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 15 / 25
Community 5 / 25

How are scores calculated?

Stars

43

Forks

2

Language

Python

License

Last pushed

Nov 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/NVlabs/blade"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.