zong's repositories
Estimating-3D-Motion-Forces
[CVPR'19 Best Paper Finalist] Extracting 3D human motion and contact forces from a single video
Parkour-dataset
A dataset with videos capturing human subjects performing four typical parkour actions. Ground truth 3D human poses and contact forces are provided.
mva-deepfool
Final project for the class Object Recognition and Computer Vision at ENS Paris
3d-pose-baseline
A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.
deepcut-cnn
CNN architecture for articulated human pose estimation
fmocap-z
A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator
graphsml
Class Project for graphsml
Grounded-Segment-Anything
Marrying Grounding DINO with Segment Anything & Stable Diffusion & BLIP - Automatically Detect , Segment and Generate Anything with Image and Text Inputs
mva-kernel-methods
kernel methods for image classification
hamer
HaMeR: Reconstructing Hands in 3D with Transformers
ManiSkill2
SAPIEN Manipulation Skill Framework, a GPU parallelized robotics simulator and benchmark
pinocchio
A fast and flexible implementation of Rigid Body Dynamics algorithms and their analytical derivatives
pose-hg-demo
Code to test and use the model from "Stacked Hourglass Networks for Human Pose Estimation"
Realtime_Multi-Person_Pose_Estimation
Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)
se3_diffusion
Implementation for SE(3) diffusion model with application to protein backbone generation
vision-based-robotic-grasping
Related papers and codes for vision-based robotic grasping