xxbbml

PixArt-sigma

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

improved-aesthetic-predictor

CLIP+MLP Aesthetic Score Predictor

Sadtalker-train

Audio-driven-TalkingFace-HeadPose

Code for "Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose" (Arxiv 2020) and "Predicting Personalized Head Movement From Short Video and Speech Signal" (TMM 2022)

roop

one-click face swap

Audio2Face

audioset_tagging_cnn

AutoTransition

[ECCV 2022] AutoTransition: Learning to Recommend Video Transition Effects

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

BasicSR

Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.

action_recognition

Solving UCF-101 with fastai2

mmdetection

OpenMMLab Detection Toolbox and Benchmark

DAIN

Depth-Aware Video Frame Interpolation (CVPR 2019)

stagesepx

detect stages in video automatically

pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

SRFlow

Official SRFlow training code: Super-Resolution using Normalizing Flow in PyTorch

fastpose

Open source library developed under python to estimate the 2D and 3D pose of people present on a video stream thourgh deep networks of convolutions.

PoseEstimationForMobile

:dancer: Real-time single person pose estimation for Android and iOS.

lightweight-human-pose-estimation.pytorch

Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.

Yet-Another-EfficientDet-Pytorch

The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.

video-nonlocal-net

Non-local Neural Networks for Video Classification

tsn-pytorch

Temporal Segment Networks (TSN) in PyTorch

MARS

MARS: Motion-Augmented RGB Stream for Action Recognition

AI_Challenger_2018

AI Challenger, a platform for open datasets and programming competitions to artificial intelligence (AI) talents around the world. https://challenger.ai/

youtube-8m

Starter code for working with the YouTube-8M dataset.

PyTorch-YOLOv3

Minimal PyTorch implementation of YOLOv3

Awesome-Crowd-Counting

Awesome Crowd Counting

Pixel2Mesh

Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images. In ECCV2018.