Neural Network Blocks - Collect all kinds of fancy model blocks for you to build more powerful neural network model.

An Improved One millisecond Mobile Backbone

Code for CVPR 2022 paper "Bailando: 3D dance generation via Actor-Critic GPT with Choreographic Memory"

SC2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration (CVPR 2022)

Recent Trackers

Automatically edit videos to post on Instagram Reels

Official code for fast face classification

A real-time motion capture system that estimates poses and global translations using only 6 inertial measurement units

ECCV2020 paper "Whole-Body Human Pose Estimation in the Wild"

[CVPR 2021, Oral] PREDATOR: Registration of 3D Point Clouds with Low Overlap.

PyTorch Implementation of the CVPR'19 Paper "Practical Full Resolution Learned Lossless Image Compression"

ppl.cv is a high-performance image processing library of openPPL supporting x86 and cuda platforms.

极简好用的 vim 配置

Development repository for the Triton language and compiler

YOLOX is a high-performance anchor-free YOLO. Exceeding yolov3~v5 with ONNX, TensorRT, NCNN, and Openvino supported.

An easy to use PyTorch to TensorRT converter

A trusty face recognition research platform developed by Tencent Youtu Lab

Object Classification Training/Inferring Framework

A library for high performance deep learning inference on NVIDIA GPUs.

PyTorch implementation of RealFormer: Transformer Likes Residual Attention

论文SAC-COT: Sample Consensus by Sampling Compatibility Triangles in Graphs for 3-D Point Cloud Registration的方法代码

深蓝三维点云处理课程

Code for HLA-Face: Joint High-Low Adaptation for Low Light Face Detection (CVPR21)

Transformer Tracking (CVPR2021)

Two-stage CenterNet

[PyTorch] Official implementation of CVPR2021 paper "PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency". https://arxiv.org/abs/2103.05465