STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation

• URL: http://arxiv.org/abs/2506.13138v2
• Date: Sat, 21 Jun 2025 07:27:24 GMT
• Title: STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation
• Authors: Jiamin Wang, Yichen Yao, Xiang Feng, Hang Wu, Yaming Wang, Qingqiu Huang, Yuexin Ma, Xinge Zhu,
• Abstract summary: STAGE is an auto-regressive framework that pioneers hierarchical feature coordination and multiphase optimization for sustainable video synthesis.<n>HTFT enhances temporal consistency between video frames throughout the video generation process.<n>We generated 600 frames of high-quality driving videos on the Nuscenes dataset, which far exceeds the maximum length achievable by existing methods.
• Score: 24.86836673853292
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The generation of temporally consistent, high-fidelity driving videos over extended horizons presents a fundamental challenge in autonomous driving world modeling. Existing approaches often suffer from error accumulation and feature misalignment due to inadequate decoupling of spatio-temporal dynamics and limited cross-frame feature propagation mechanisms. To address these limitations, we present STAGE (Streaming Temporal Attention Generative Engine), a novel auto-regressive framework that pioneers hierarchical feature coordination and multi-phase optimization for sustainable video synthesis. To achieve high-quality long-horizon driving video generation, we introduce Hierarchical Temporal Feature Transfer (HTFT) and a novel multi-stage training strategy. HTFT enhances temporal consistency between video frames throughout the video generation process by modeling the temporal and denoising process separately and transferring denoising features between frames. The multi-stage training strategy is to divide the training into three stages, through model decoupling and auto-regressive inference process simulation, thereby accelerating model convergence and reducing error accumulation. Experiments on the Nuscenes dataset show that STAGE has significantly surpassed existing methods in the long-horizon driving video generation task. In addition, we also explored STAGE's ability to generate unlimited-length driving videos. We generated 600 frames of high-quality driving videos on the Nuscenes dataset, which far exceeds the maximum length achievable by existing methods.

Related papers

• Temporal In-Context Fine-Tuning for Versatile Control of Video Diffusion Models [34.131515004434846]
  We introduce Temporal In-Context Fine-Tuning (TIC-FT), an efficient approach for adapting pretrained video diffusion models to conditional generation tasks.<n>TIC-FT requires no architectural changes and achieves strong performance with as few as 10-30 training samples.<n>We validate our method across a range of tasks, including image-to-video and video-to-video generation, using large-scale base models such as CogVideoX-5B and Wan-14B.
  arXiv  Detail & Related papers  (2025-06-01T12:57:43Z)
• Generative Pre-trained Autoregressive Diffusion Transformer [54.476056835275415]
  GPDiT is a Generative Pre-trained Autoregressive Diffusion Transformer.<n>It unifies the strengths of diffusion and autoregressive modeling for long-range video synthesis.<n>It autoregressively predicts future latent frames using a diffusion loss, enabling natural modeling of motion dynamics.
  arXiv  Detail & Related papers  (2025-05-12T08:32:39Z)
• DiVE: Efficient Multi-View Driving Scenes Generation Based on Video Diffusion Transformer [56.98400572837792]
  DiVE produces high-fidelity, temporally coherent, and cross-view consistent multi-view videos.<n>These innovations collectively achieve a 2.62x speedup with minimal quality degradation.
  arXiv  Detail & Related papers  (2025-04-28T09:20:50Z)
• RAGME: Retrieval Augmented Video Generation for Enhanced Motion Realism [73.38167494118746]
  We propose a framework to improve the realism of motion in generated videos.<n>We advocate for the incorporation of a retrieval mechanism during the generation phase.<n>Our pipeline is designed to apply to any text-to-video diffusion model.
  arXiv  Detail & Related papers  (2025-04-09T08:14:05Z)
• Tuning-Free Multi-Event Long Video Generation via Synchronized Coupled Sampling [81.37449968164692]
  We propose Synchronized Coupled Sampling (SynCoS), a novel inference framework that synchronizes denoising paths across the entire video.<n>Our approach combines two complementary sampling strategies, which ensure seamless local transitions and enforce global coherence.<n>Extensive experiments show that SynCoS significantly improves multi-event long video generation, achieving smoother transitions and superior long-range coherence.
  arXiv  Detail & Related papers  (2025-03-11T16:43:45Z)
• AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion [19.98565541640125]
  We introduce Auto-Regressive Diffusion (AR-Diffusion), a novel model that combines the strengths of auto-regressive and diffusion models for flexible video generation.<n>Inspired by auto-regressive generation, we incorporate a non-decreasing constraint on the corruption timesteps of individual frames.<n>This setup, together with temporal causal attention, enables flexible generation of videos with varying lengths while preserving temporal coherence.
  arXiv  Detail & Related papers  (2025-03-10T15:05:59Z)
• Efficient Long-duration Talking Video Synthesis with Linear Diffusion Transformer under Multimodal Guidance [19.590464986176617]
  LetsTalk is a diffusion diffusion TranSformer for Talking video synthesis.<n>Our approach achieves state-of-the-art generation quality, producing temporally coherent and realistic videos.
  arXiv  Detail & Related papers  (2024-11-24T04:46:00Z)
• MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control [68.74166535159311]
  MagicDrive-V2 is a novel approach that integrates the MVDiT block and spatial-temporal conditional encoding to enable multi-view video generation and precise geometric control.<n>It enables multi-view driving video synthesis with $3.3times$ resolution and $4times$ frame count (compared to current SOTA), rich contextual control, and geometric controls.
  arXiv  Detail & Related papers  (2024-11-21T03:13:30Z)
• Anchored Diffusion for Video Face Reenactment [17.343307538702238]
  We introduce Anchored Diffusion, a novel method for synthesizing relatively long and seamless videos. We train our model on video sequences with random non-uniform temporal spacing and incorporate temporal information via external guidance. During inference, we leverage the transformer architecture to modify the diffusion process, generating a batch of non-uniform sequences anchored to a common frame.
  arXiv  Detail & Related papers  (2024-07-21T13:14:17Z)
• RAVEN: Rethinking Adversarial Video Generation with Efficient Tri-plane Networks [93.18404922542702]
  We present a novel video generative model designed to address long-term spatial and temporal dependencies. Our approach incorporates a hybrid explicit-implicit tri-plane representation inspired by 3D-aware generative frameworks. Our model synthesizes high-fidelity video clips at a resolution of $256times256$ pixels, with durations extending to more than $5$ seconds at a frame rate of 30 fps.
  arXiv  Detail & Related papers  (2024-01-11T16:48:44Z)
• Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution [65.91317390645163]
  Upscale-A-Video is a text-guided latent diffusion framework for video upscaling. It ensures temporal coherence through two key mechanisms: locally, it integrates temporal layers into U-Net and VAE-Decoder, maintaining consistency within short sequences. It also offers greater flexibility by allowing text prompts to guide texture creation and adjustable noise levels to balance restoration and generation.
  arXiv  Detail & Related papers  (2023-12-11T18:54:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.