lyupei

self-llm

《开源大模型食用指南》基于Linux环境快速部署开源大模型，更适合**宝宝的部署教程

gpupixel

Real-time image and video processing library similar to GPUImage, with built-in beauty filters, achieving commercial-grade beauty effects. Written in C++11 and based on OpenGL/ES.

segmentation_models.pytorch

Segmentation models with pretrained backbones. PyTorch.

easyportrait

EasyPortrait - Face Parsing and Portrait Segmentation Dataset

SCTNet

Official implementation of SCTNet (AAAI2024)

VIM

understand-prompt

【🔞🔞🔞 内含不适合未成年人阅读的图片】基于我擅长的编程、绘画、写作展开的 AI 探索和总结：StableDiffusion 是一种强大的图像生成模型，能够通过对一张图片进行演化来生成新的图片。ChatGPT 是一个基于 Transformer 的语言生成模型，它能够自动为输入的主题生成合适的文章。而 Github Copilot 是一个智能编程助手，能够加速日常编程活动。

FFHQ-UV

The official repository of our CVPR2023 paper "FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction".

wholebody3d

Official repository of Human3.6M 3D WholeBody (H3WB) dataset

JDRL

The implementation of "Learning Single Image Defocus Deblurring with Misaligned Training Pairs".

MemSeg

Unofficial re-implementation of MemSeg for Anomaly Detection

deep-focus-matting

A trimap free approach to portrait image matting using DeepLabv3+ with asymmetric decoders and shared encoder architecture.

megvii-tsinghua-dl-course

Slides with modifications for a course at Tsinghua University.

PyMAF-X

[TPAMI 2023] PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images

ml-neuman

Official repository of NeuMan: Neural Human Radiance Field from a Single Video (ECCV 2022)

Sparsebit

A model compression and acceleration toolbox based on pytorch.

CtrlHair

Controllable Hair Editing (ECCV 2022)

CelebV-HQ

[ECCV 2022] CelebV-HQ: A Large-Scale Video Facial Attributes Dataset

omni3d

Code release for "Omni3D A Large Benchmark and Model for 3D Object Detection in the Wild"

fite

eccv 2022

Gen6D

[ECCV2022] Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images

VISO

[IEEE TGRS 2021] Detecting and Tracking Small and Dense Moving Objects in Satellite Videos: A Benchmark

ProLiF

[Code ongoing] Progressively-connected light field network for efficient view synthesis

UNIF

[ECCV 2022] The official repo for the paper "UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation".

Awesome-ECCV2022-Low-Level-Vision

A Collection of Papers and Codes in ECCV2022 about low level vision

litepose

[CVPR'22] Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation

vidar

SwissArmyTransformer

SwissArmyTransformer is a flexible and powerful library to develop your own Transformer variants.

VIPSeg-Dataset

CVPR2022: Large-scale Video Panoptic Segmentation in the Wild: A Benchmark

InstMatt

Official repository for Instance Human Matting via Mutual Guidance and Multi-Instance Refinement