🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

🧑‍🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gan…

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

CVPR 2022 论文和开源项目合集

[NeurIPS 2023] This repo contains the code for our paper Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.

Viewer for point cloud data, support LAS, pcd, ply etc.

PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

(CRNN) Chinese Characters Recognition.

A pytorch re-implementation of Real-time Scene Text Detection with Differentiable Binarization

Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D (ECCV 2020)

[ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

OpenMMLab's next-generation platform for general 3D object detection.

End-to-End Object Detection with Transformers

[ICCV 2023] Cross Modal Transformer: Towards Fast and Robust 3D Object Detection

OpenMMLab Detection Toolbox and Benchmark

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

restruct the apriltag using python

State-of-the-art 2D and 3D Face Analysis Project

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

Fast-BEV: A Fast and Strong Bird’s-Eye View Perception Baseline

Awesome papers about Multi-Camera 3D Object Detection and Segmentation in Bird's-Eye-View, such as DETR3D, BEVDet, BEVFormer, BEVDepth, UniAD

Vision-Centric BEV Perception: A Survey

The repository containing tools and information about the WoodScape dataset.

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

An academic alternative to Tesla's occupancy network for autonomous driving.

A PyTorch implementation of "Real-time Scene Text Detection with Differentiable Binarization".