BEVDet implemented by TensorRT, C++； Achieving real-time performance on Orin

[ICLR24] Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control”

[ICLR 2023 & TPAMI 2025] S-NeRF: Neural Radiance Fields for Street Views

[CVPR 2023] An academic alternative to Tesla's occupancy network for autonomous driving.

Detachable Novel Views Synthesis of Dynamic Scenes Using Distribution-Driven Neural Radiance Fields

[ECCV 2022] Official PyTorch Code of DEVIANT: Depth Equivariant Network for Monocular 3D Object Detection

Code base of the BEVDet series .

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

Official Repo for Ground-aware Monocular 3D Object Detection for Autonomous Driving / YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection

(ICLR 2022 Spotlight) Official PyTorch implementation of "How Do Vision Transformers Work?"

Official code for Conformer: Local Features Coupling Global Representations for Visual Recognition

Standardizing weights to accelerate micro-batch training

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Download images from Google, Bing, Baidu. 谷歌、百度、必应图片下载.

Object Classification Training Framework

You Only Look One-level Feature (YOLOF), CVPR2021, Detectron2

🔥 2D and 3D Face alignment library build using pytorch

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

[CVPR2021, PAMI2023] End-to-End Object Detection with Learnable Proposal

Disentangled Non-Local Neural Networks

Official repository for the "Big Transfer (BiT): General Visual Representation Learning" paper.

End-to-End Object Detection with Fully Convolutional Network

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

OpenMMLab Detection Toolbox and Benchmark

A library for real-time video stream decoding to CUDA memory

CVPR 2025 论文和开源项目合集

Implementation of popular deep learning networks with TensorRT network definition API