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

A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution…

VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking (CVPR 2023)

The devkit of the nuScenes dataset.

Code for a series of work in LiDAR perception, including SST (CVPR 22), FSD (NeurIPS 22), FSD++ (TPAMI 23), FSDv2, and CTRL (ICCV 23, oral).

Implementation for CenterFormer: Center-based Transformer for 3D Object Detection (ECCV 2022)

An Efficient, Flexible, and General deep learning framework that retains minimal.

Code base for M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers

OpenMMLab Detection Toolbox and Benchmark

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

Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

Official PyTorch implementation of VoxFormer [CVPR 2023 Highlight]

LLM inference in C/C++

Repository for GHOST: Simple Cues Lead to a Strong Multi-Object Tracker (CVPR 2023)

[CVPR2023] MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors

Global Tracking Transformers, CVPR 2022

ECCV 2024 论文和开源项目合集，同时欢迎各位大佬提交issue，分享ECCV 2024论文和开源项目

ICCV 2023 论文和开源项目合集

cvpr2024/cvpr2023/cvpr2022/cvpr2021/cvpr2020/cvpr2019/cvpr2018/cvpr2017 论文/代码/解读/直播合集，极市团队整理

Bringing Old Photo Back to Life (CVPR 2020 oral)

Implementation of "TrackFormer: Multi-Object Tracking with Transformers”. [Conference on Computer Vision and Pattern Recognition (CVPR), 2022]

We use hybrid a star and optimization-based method for trajectory planning of the autonomous vehicle parking

[IEEE T-PAMI] Awesome BEV perception research and cookbook for all level audience in autonomous diriving

Visual tracking library based on PyTorch.

[ECCV2022] MOTR: End-to-End Multiple-Object Tracking with TRansformer

Self-Supervised Pillar Motion Learning for Autonomous Driving (CVPR 2021)

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking