Glad: A Streaming Scene Generator for Autonomous Driving
Bin Xie, Yingfei Liu, Tiancai Wang, Jiale Cao, Xiangyu Zhang
Abstract
The generation and simulation of diverse real-world scenes have significant application value in the field of autonomous driving, especially for the corner cases. Recently, researchers have explored employing neural radiance fields or diffusion models to generate novel views or synthetic data under driving scenes. However, these approaches suffer from unseen scenes or restricted video length, thus lacking sufficient adaptability for data generation and simulation. To address these issues, we propose a simple yet effective framework, named Glad, to generate video data in a frame-by-frame style. To ensure the temporal consistency of synthetic video, we introduce a latent variable propagation module, which views the latent features of previous frame as noise prior and injects it into the latent features of current frame. In addition, we design a streaming data sampler to orderly sample the original image in a video clip at continuous iterations. Given the reference frame, our Glad can be viewed as a streaming simulator by generating the videos for specific scenes. Extensive experiments are performed on the widelyused nuScenes dataset. Experimental results demonstrate that our proposed Glad achieves promising performance, serving as a strong baseline for online video generation. We will release the source code and models publicly.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
4 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Probabilistic Models
- CorrectAD: A Self-Correcting Agentic System to Improve End-to-end Planning in Autonomous Driving cites High-Resolution Image Synthesis with Latent Diffusion Models
- CorrectAD: A Self-Correcting Agentic System to Improve End-to-end Planning in Autonomous Driving cites Adding Conditional Control to Text-to-Image Diffusion Models
- CorrectAD: A Self-Correcting Agentic System to Improve End-to-end Planning in Autonomous Driving cites OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving
- Adding Conditional Control to Text-to-Image Diffusion Models cites High-Resolution Image Synthesis with Latent Diffusion Models
- Adding Conditional Control to Text-to-Image Diffusion Models cites Learning Transferable Visual Models From Natural Language Supervision
- OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving cites High-Resolution Image Synthesis with Latent Diffusion Models
- OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving cites Adding Conditional Control to Text-to-Image Diffusion Models
- OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving cites Denoising Diffusion Probabilistic Models
- X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability cites High-Resolution Image Synthesis with Latent Diffusion Models
- X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability cites Directly Denoising Diffusion Models
- X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability cites Denoising Diffusion Probabilistic Models
- Directly Denoising Diffusion Models cites High-Resolution Image Synthesis with Latent Diffusion Models
- Directly Denoising Diffusion Models cites Denoising Diffusion Probabilistic Models
Cited by top-tier papers4
- From Forecasting to Planning: Policy World Model for Collaborative State-Action PredictionZhida Zhao, Talas Fu, Yifan Wang, Lijun Wang et al.NeurIPS 2025 · 36 citations
- X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible ControllabilityYu Yang, Alan Liang, Jianbiao Mei, Yukai Ma et al.NeurIPS 2025 · 22 citations
- OmniGen: Unified Multimodal Sensor Generation for Autonomous DrivingTao Tang, Enhui Ma, Xia Zhou, Letian Wang et al.ACM MM 2025 · 1 citation
- CorrectAD: A Self-Correcting Agentic System to Improve End-to-end Planning in Autonomous DrivingEnhui Ma, Lijun Zhou, Tao Tang, Jiahuan Zhang et al.AAAI 2026
Builds on28
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Directly Denoising Diffusion ModelsDan Zhang, Jingjing Wang, Feng LuoICML 2024 · 11,724 citations
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 6,759 citations
Related papers
- WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous DrivingZiyue Zhu, Zhanqian Wu, Zhenxin Zhu, Lijun Zhou et al.ICLR 2026 · 11 citations
- SimGen: Simulator-conditioned Driving Scene GenerationYunsong Zhou, Michael Simon, Zhenghao Mark Peng, Sicheng Mo et al.NeurIPS 2024 · 44 citations
- Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal ConsistencyXiangyu Guo, Zhanqian Wu, Kaixin Xiong, Ziyang Xu et al.NeurIPS 2025 · 24 citations
- Autoscape: Geometry-Consistent Long-Horizon Scene GenerationJiacheng Chen, Ziyu Jiang, Mingfu Liang, Bingbing Zhuang et al.ICCV 2025
- NeuRAD: Neural Rendering for Autonomous DrivingAdam Tonderski, Carl Lindström, Georg Hess, William Ljungbergh et al.CVPR 2024 · 58 citations
