Rui Song

EnerGS. [ICML 2026] EnerGS for 3D Rconstruction with Partial Geometric Priors

lightly-studio. Curate, Annotate, and Manage Your Data in LightlyStudio.

CoDa-4DGS. [ICCV 2025] CoDa-4DGS: Dynamic Gaussian Splatting with Context and Deformation Awareness for Autonomous Driving

AD-GS. [ICCV 2025] Official implementation of "AD-GS: Object-Aware B-Spline Gaussian Splatting for Self-Supervised Autonomous Driving"

V2X-Guassians. [IEEE-IV 2025] V2X-Gaussians: Gaussian Splatting for Multi-Agent Cooperative Dynamic Scene Reconstruction

awesome-v2x-datasets.

GaussianFormer. [ECCV 2024] Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction

Hierarchical-Localization. Visual localization made easy with hloc

ros_etsi_its_msgs. ROS equivalents of ETSI ITS messages (CAM and DENM)

COALA. COALA: A Practical and Vision-Centric Federated Learning Platform, accepted to ICML'24

tumtraf-a. JavaScript

ROS-LLM. ROS-LLM is a framework designed for embodied intelligence applications in ROS. It allows natural language interactions and leverages Large Language Models (LLMs) for decision-making and robot control. With an easy configuration process, this framework allows for swift integration, enabling your robot to operate with it in as little as ten minutes.

world-creator. LLM-based CLI utility for simulation worlds creation.

ollama. Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

LOTVS-MM-AU. [CVPR2024 Highlight] The official repo for paper "Abductive Ego-View Accident Video Understanding for Safe Driving Perception"

CoHFF. [CVPR 2024] Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehicles

MagicDrive3D. Official implementation of the paper “MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes”

LAW. (ICLR2025) Enhancing End-to-End Autonomous Driving with Latent World Model

Drive-WM. [CVPR 2024] A world model for autonomous driving.

coopdet3d. Python

pFedMe. Personalized Federated Learning with Moreau Envelopes (pFedMe) using Pytorch (NeurIPS 2020)

PFLlib. Master Federated Learning in 2 Hours—Run It on Your PC!

PointTransformerV3. [CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)

TFCO. Official Code for "Temporal Enhanced Floating Car Observers" presented at IV2024

blades. ⚔️ Blades: A Unified Benchmark Suite for Attacks and Defenses in Federated Learning

deep_meta-learning_guidance_law. Code for paper "Learning to Guide: Guidance Law Based on Deep Meta-learning and Model Predictive Path Integral Control"

panacea. [CVPR2024] Official Repository of Paper "Panacea: Panoramic and Controllable Video Generation for Autonomous Driving"

Awesome-Papers-World-Models-Autonomous-Driving. Awesome Papers about World Models in Autonomous Driving

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

LiDAR-Diffusion. [CVPR 2024] Official implementation of "Towards Realistic Scene Generation with LiDAR Diffusion Models"

HEAL. [ICLR2024] HEAL: An Extensible Framework for Open Heterogeneous Collaborative Perception ➡️ All You Need for Multi-Modality Collaborative Perception!

yolov9. Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

Collaborative_Perception. This repository is a paper digest of recent advances in collaborative / cooperative / multi-agent perception for V2I / V2V / V2X autonomous driving scenario.

VAD. [ICCV 2023 & ICLR 2026] VAD: Vectorized Scene Representation for Efficient Autonomous Driving

efficientvit. Efficient vision foundation models for high-resolution generation and perception.

3DObjectTracking. Algorithms and Publications on 3D Object Tracking

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

labelCloud. A lightweight tool for labeling 3D bounding boxes in point clouds.

Calibration-Is-All-You-Need. calibration is you need including camera、imu、camera2camera、 camera2lidar、imu2camera、imu2lidar.

PaddleFL. Federated Deep Learning in PaddlePaddle

PPGeo. [ICLR 2023] Pytorch implementation of PPGeo, a fully self-supervised driving policy pre-training framework to learn from unlabeled driving videos.

FedBEVT. Federated Learning for Bird's Eye View Perception Based on Multi-Camera Data

ResFed. Residual-based Federated Learning Framework

Awesome-Federated-Learning-for-Autonomous-Driving. FedML for Autonomous Driving (AD), Intelligent Transportation Systems (ITS), Connected and Automated Vehicles (CAV)

OVAL-Assets. OVAL Marketplace

3d-bat. 3D Bounding Box Annotation Tool (3D-BAT) Point cloud and Image Labeling

Instant-angelo. Instant-angelo: Build high-fidelity Digital Twin within 20 Minutes!

Awesome-Occupancy-Prediction-Autonomous-Driving. Awesome papers about Multi-Camera Semantic Occupancy Prediction, such as TPVFormer, OccFormer, Occ3D, OpenOccupancy

Awesome-Federated-Machine-Learning. Everything about federated learning, including research papers, books, codes, tutorials, videos and beyond

FedD3. FedD3: Federated Learning via Decentralized Dataset Distillation

Transformer-in-Computer-Vision. A paper list of some recent Transformer-based CV works.

pytorch_federated_learning. PyTorch Federated Learning (easy to use and extend)

simple_perception. Make SOTA AV perception algorithms easy to learn and use

CoBEVT. [CoRL2022] CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers

H2-Fed. PyTorch implementation of H2-Fed Federated Learning Framework

leaf. Leaf: A Benchmark for Federated Settings

Awesome-Dataset-Distillation. A curated list of awesome papers on dataset distillation and related applications.

OpenCOOD. [ICRA 2022] An opensource framework for cooperative detection. Official implementation for OPV2V.

v2x-vit. [ECCV2022] Official Implementation of paper "V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer"

Awesome-Visual-Transformer. Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)

InTAS. InTAS is the Ingolstadt traffic scenario for SUMO, which was designed, developed and validated with real traffic data from measuring points.

DNN_param_encode. Python

mtt-distillation. Official code for our CVPR '22 paper "Dataset Distillation by Matching Training Trajectories"

Awesome-Federated-Learning. FedML - The Research and Production Integrated Federated Learning Library: https://fedml.ai