盘一盘扩散模型在自动驾驶中的应用！综述&论文汇总~

点击下方卡片，关注“自动驾驶之心”公众号

戳我-> 领取自动驾驶近15个方向学习路线

扩散模型近期在自动驾驶方向的工作越来越多，除了传统的生成方向，目前已经扩展到端到端、语义分割、轨迹预测、规划控制等等很多子方向。目前自动驾驶扩散模型的趋势已成，为此自动驾驶之心汇总了相关综述和论文，更多详细资料欢迎加入『自动驾驶之心知识星球』获取全部资料！

综述

Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices

• 论文链接：https://arxiv.org/abs/2410.11795

Diffusion Models in 3D Vision: A Survey

• 论文链接：https://arxiv.org/abs/2410.04738

Conditional Image Synthesis with Diffusion Models: A Survey

• 论文链接：https://arxiv.org/abs/2409.19365

Trustworthy Text-to-Image Diffusion Models: A Timely and Focused Survey

• 论文链接：https://arxiv.org/abs/2409.18214

A Survey on Diffusion Models for Recommender Systems

• 论文链接：https://arxiv.org/abs/2409.05033

Diffusion-Based Visual Art Creation: A Survey and New Perspectives

• 论文链接：https://arxiv.org/abs/2408.12128

Replication in Visual Diffusion Models: A Survey and Outlook

• 论文链接：https://arxiv.org/abs/2408.00001

Diffusion Model-Based Video Editing: A Survey

• 论文链接：https://arxiv.org/abs/2407.07111

Diffusion Models and Representation Learning: A Survey

• 论文链接：https://arxiv.org/abs/2407.00783

A Survey of Multimodal-Guided Image Editing with Text-to-Image Diffusion Models

• 论文链接：https://arxiv.org/abs/2406.14555

Diffusion Models in Low-Level Vision: A Survey

• 论文链接：https://arxiv.org/abs/2406.11138

Video Diffusion Models: A Survey

• 论文链接：https://arxiv.org/abs/2405.03150

A Survey on Diffusion Models for Time Series and Spatio-Temporal Data

• 论文链接：https://arxiv.org/abs/2404.18886

Controllable Generation with Text-to-Image Diffusion Models: A Survey

• 论文链接：https://arxiv.org/abs/2403.04279

Diffusion Model-Based Image Editing: A Survey

• 论文链接：https://arxiv.org/abs/2402.17525

Diffusion Models, Image Super-Resolution And Everything: A Survey

• 论文链接：https://arxiv.org/abs/2401.00736

A Survey on Video Diffusion Models

• 论文链接：https://arxiv.org/abs/2310.10647

A Survey of Diffusion Models in Natural Language Processing

• 论文链接：https://arxiv.org/abs/2305.14671

自动驾驶中的扩散模型

OLiDM: Object-aware LiDAR Diffusion Models for Autonomous Driving

• 论文链接：https://arxiv.org/abs/2412.17226

SynDiff-AD: Improving Semantic Segmentation and End-to-End Autonomous Driving with Synthetic Data from Latent Diffusion Models

• 论文链接：https://arxiv.org/abs/2411.16776

Characterized Diffusion Networks for Enhanced Autonomous Driving Trajectory Prediction

• 论文链接：https://arxiv.org/abs/2411.16457

DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving

• 论文链接：https://arxiv.org/abs/2411.15139

Efficient Domain Augmentation for Autonomous Driving Testing Using Diffusion Models

• 论文链接：https://arxiv.org/abs/2409.13661

DriveDiTFit: Fine-tuning Diffusion Transformers for Autonomous Driving

• 论文链接：https://arxiv.org/abs/2407.15661

VQA-Diff: Exploiting VQA and Diffusion for Zero-Shot Image-to-3D Vehicle Asset Generation in Autonomous Driving

• 论文链接：https://arxiv.org/abs/2407.06516

Enhanced Safety in Autonomous Driving: Integrating Latent State Diffusion Model for End-to-End Navigation

• 论文链接：https://arxiv.org/abs/2407.06317

Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following

• 论文链接：https://arxiv.org/abs/2402.06559

Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion

• 论文链接：https://arxiv.org/abs/2311.01017