tqxli

dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

awesome-neuro-ai-papers

Papers from the intersection of deep learning and neuroscience

NPYViewer

Load and view .npy files containing 2D and 1D NumPy arrays.

DSNeRF

Code release for DS-NeRF (Depth-supervised Neural Radiance Fields)

evotorch

Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.

clip-video-encode

Easily compute clip embeddings from video frames

nerfstudio

A collaboration friendly studio for NeRFs

manopth

MANO layer for PyTorch, generating hand meshes as a differentiable layer

VAME

Variational Animal Motion Embedding - A tool for time series embedding and clustering

hiplot

HiPlot makes understanding high dimensional data easy

Snipper

This is the re-implementation of paper "Snipper: A Spatiotemporal Transformer for Simultaneous Multi-Person 3D Pose Estimation Tracking and Forecasting on a Video Snippet"

IntagHand

csGraduateFellowships

A curated list of fellowships for graduate students in Computer Science and related fields.

CenterPoint

UNETR-Pose

3D Multi-person Pose Estimation in Multi-view Environment using 3D U-Net Transformer Networks

animal_papers

Awesome papers for markerless animal motion capture and 3D reconstruction.

pyk4a

Python 3 wrapper for Azure-Kinect-Sensor-SDK

Label3D

Labeling GUI for multi-camera tracking

HOPE

Source code of CVPR 2020 paper, "HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation"

humor

Code for ICCV 2021 paper "HuMoR: 3D Human Motion Model for Robust Pose Estimation"

behave-dataset

Code to access BEHAVE dataset, CVPR'22

PHALP

Code repository for the paper "Tracking People by Predicting 3D Appearance, Location & Pose". (CVPR 2022 Oral)

MultiMotion

Multi-Person Extreme Motion Prediction

NeuralGraph

Official implementation for CVPR'2021 paper Neural Deformation Graphs

Awesome-Temporal-Action-Localization

A curated list of temporal action localization/detection and related area (e.g. temporal action proposal) resources.

vidat

Video Annotation Tool

VolumetricCapture

A multi-sensor capture system for free viewpoint video.

OcclusionFusion

OcclusionFusion: realtime dynamic 3D reconstruction based on single-view RGB-D

EasyMocap

Make human motion capture easier.

NodeNorm