Awesome List of Attention Modules and Plug&Play Modules in Computer Vision

[IROS24] Temporal-and Viewpoint-Invariant Registration for Under-Canopy Footage using Deep-Learning-based Bird's-Eye View Prediction

Efficient and lightweight Vision-Language model for Visual Question Answering in autonomous driving scenarios. The approach replaces images in BLIP's architecture with spatio-temporal BEV feature maps

[ECCV 2024] RecurrentBEV: A Long-term Temporal Fusion Framework for Multi-view 3D Detection

ChatReviewer: 使用ChatGPT分析论文优缺点，提出改进建议

[ICLR 2025] Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving

MetaOcc: Surround-View 4D Radar and Camera Fusion Framework for 3D Occupancy Prediction with Dual Training Strategies

[ICRA 2024] Official code for BEVUDA: Multi-geometric Space Alignments for Domain Adaptive BEV 3D Object Detection

A plugin to make view transformer from perspective view to bird-eye-view, it is used in bevdet

[ECCV2024] This is the official implementation of GraphBEV, a BEV multi-modal framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

Gaga: Group Any Gaussians via 3D-aware Memory Bank

[CVPR 2025 Almost Oral ; )] GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding

GaussianAD: Gaussian-Centric End-to-End Autonomous Driving

Official Code Release for "Towards Flexible 3D Perception: Object-Centric Occupancy Completion Augments 3D Object Detection" in NeurIPS 2024

[AAAI 2025] ProtoOcc: Accurate, Efficient 3D Occupancy Prediction Using Dual Branch Encoder-Prototype Query Decoder

UniDrive: Towards Universal Driving Perception Across Camera Configurations

Language Driven Occupancy Prediction

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

[3DV 2025] LSSInst: Improving Geometric Modeling in LSS-Based BEV Perception with Instance Representation

[WACV 2024 Survey Paper] Multimodal Large Language Models for Autonomous Driving

CIGOcc: Complementary Information Guided Occupancy Prediction via Multi-Level Representation Fusion

GussianPretrain for Visual Pre-training in Autonomous Driving, showcasing significant improvements across various 3D perception tasks, including 3D object detection, HD-map construction, and Occupa…