llj928842319

fastai

The fastai deep learning library

rle-human-pose-regression

Based on "Human Pose Regression with Residual Log-likelihood Estimation"

ICON

[CVPR'22] ICON: Implicit Clothed humans Obtained from Normals

torchscale

Foundation Architecture for (M)LLMs

tfrecord

Standalone TFRecord reader/writer with PyTorch data loaders

contiguous_pytorch_params

Accelerate training by storing parameters in one contiguous chunk of memory.

RetNet

Huggingface compatible implementation of RetNet (Retentive Networks, https://arxiv.org/pdf/2307.08621.pdf) including parallel, recurrent, and chunkwise forward.

EANet

mae

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

ICCV-2023-Papers

res-loglikelihood-regression

Code for "Human Pose Regression with Residual Log-likelihood Estimation", ICCV 2021 Oral

Click-Pose

[ICCV 2023] Official implementation of the paper "Neural Interactive Keypoint Detection"

CenterNet

Object detection, 3D detection, and pose estimation using center point detection:

nosmpl

Accelerated SMPL operation, commonly used in generate 3D human mesh, STAR included.

das

Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation

PyTorchTricks

Some tricks of pytorch... :star:

omnimotion

pykalman

Kalman Filter, Smoother, and EM Algorithm for Python

kypt_transformer

DIR

[ICCV 2023 Oral] Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Image

human-motion-capture

collect papers about human motion capture

EasyMocap

Make human motion capture easier.

BMP

[CVPR 2021] Body Meshes as Points.

HierarchicalProbabilistic3DHuman

Code repository for the paper: Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild (ICCV 2021)

ProPose

Code for "Learning Analytical Posterior Probability for Human Mesh Recovery" (CVPR 2023)

DynaCam

[CVPR 2023] DynaCam dataset - 3D human trajectories in global coordinates from videos captured by dynamic cameras

ROMP

Monocular, One-stage, Regression of Multiple 3D People and their 3D positions & trajectories in camera & global coordinates. ROMP[ICCV21], BEV[CVPR22], TRACE[CVPR2023]

NIKI

Code of "NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation", CVPR 2023

render_mano_ih

expose

ExPose - EXpressive POse and Shape rEgression