PulseAugur
EN
LIVE 11:59:56

New AI Frameworks Enhance Autonomous Driving Scene Generation

By PulseAugur Editorial · [6 sources] ·

Researchers have introduced several new frameworks for generating realistic and controllable driving scenes, crucial for training autonomous vehicles. DriveWAM adapts video diffusion transformers to create autoregressive action policies, incorporating scene understanding and memory for long-horizon planning. AnyScene offers a unified occupancy-centric approach, enabling precise control from arbitrary BEV layouts and generating temporally consistent multi-view videos. DriveGen3D combines efficient video diffusion with 3D scene reconstruction for high-quality, controllable dynamic scenes, supporting long driving videos and 3D representations. Additionally, a new dataset, Nuplan-Occ, has been curated to facilitate large-scale generative modeling and downstream applications in autonomous driving. AI

IMPACT These advancements in synthetic data generation could accelerate the development and testing of autonomous driving systems by providing more realistic and controllable training environments.

RANK_REASON Multiple research papers introducing new methods and datasets for driving scene generation.

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 6 sources. How we write summaries →

COVERAGE [6]

  1. arXiv cs.CV TIER_1 English(EN) · Chen Shi, Jinrui Xu, Shaoshuai Shi, Kehua Sheng, Bo Zhang, Li Jiang ·

    DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving

    arXiv:2605.28544v1 Announce Type: new Abstract: Pretrained foundation models have become an important basis for end-to-end autonomous driving. In contrast to vision-language models pretrained primarily on static image-text pairs, video generative models capture temporal dynamics …

  2. arXiv cs.CV TIER_1 English(EN) · Li Jiang ·

    DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving

    Pretrained foundation models have become an important basis for end-to-end autonomous driving. In contrast to vision-language models pretrained primarily on static image-text pairs, video generative models capture temporal dynamics and motion priors that are naturally suited for …

  3. arXiv cs.CV TIER_1 English(EN) · Haiming Zhang, Junfei Zhou, Feng Jiang, Jingzhong Li, Zhenglong Guo, Penglin Dai, Jifeng Dai, Yan Xie, Benjin Zhu ·

    AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and Beyond

    arXiv:2605.26113v1 Announce Type: cross Abstract: Generating high-fidelity and controllable synthetic data is critical for advancing end-to-end autonomous driving, particularly for addressing the long tail of rare safety-critical scenarios. Existing occupancy-guided methods typic…

  4. arXiv cs.CV TIER_1 English(EN) · Weijie Wang, Jiagang Zhu, Zeyu Zhang, Xiaofeng Wang, Zheng Zhu, Guosheng Zhao, Chaojun Ni, Haoxiao Wang, Guan Huang, Xinze Chen, Yukun Zhou, Wenkang Qin, Duochao Shi, Haoyun Li, Yicheng Xiao, Donny Y. Chen, Jiwen Lu ·

    DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion

    arXiv:2510.15264v3 Announce Type: replace Abstract: We present DriveGen3D, a novel framework for generating high-quality and highly controllable dynamic 3D driving scenes that addresses critical limitations in existing methodologies. Current approaches to driving scene synthesis …

  5. arXiv cs.CV TIER_1 English(EN) · Bohan Li, Xin Jin, Hu Zhu, Hongsi Liu, Ruikai Li, Jiazhe Guo, Kaiwen Cai, Chao Ma, Yueming Jin, Hao Zhao, Xiaokang Yang, Wenjun Zeng ·

    Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method

    arXiv:2510.22973v2 Announce Type: replace Abstract: Driving scene generation is a critical domain for autonomous driving, enabling downstream applications, including perception and planning evaluation. Occupancy-centric methods have recently achieved state-of-the-art results by o…

  6. arXiv cs.CV TIER_1 English(EN) · Benjin Zhu ·

    AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and Beyond

    Generating high-fidelity and controllable synthetic data is critical for advancing end-to-end autonomous driving, particularly for addressing the long tail of rare safety-critical scenarios. Existing occupancy-guided methods typically rely on shallow conditioning mechanisms and r…

RELATED ENTITIES

RELATED TOPICS