{"ID":2879944,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.15720","arxiv_id":"2508.15720","title":"WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception","abstract":"Generative video modeling has made significant strides, yet ensuring structural and temporal consistency over long sequences remains a challenge. Current methods predominantly rely on RGB signals, leading to accumulated errors in object structure and motion over extended durations. To address these issues, we introduce WorldWeaver, a robust framework for long video generation that jointly models RGB frames and perceptual conditions within a unified long-horizon modeling scheme. Our training framework offers three key advantages. First, by jointly predicting perceptual conditions and color information from a unified representation, it significantly enhances temporal consistency and motion dynamics. Second, by leveraging depth cues, which we observe to be more resistant to drift than RGB, we construct a memory bank that preserves clearer contextual information, improving quality in long-horizon video generation. Third, we employ segmented noise scheduling for training prediction groups, which further mitigates drift and reduces computational cost. Extensive experiments on both diffusion- and rectified flow-based models demonstrate the effectiveness of WorldWeaver in reducing temporal drift and improving the fidelity of generated videos.","short_abstract":"Generative video modeling has made significant strides, yet ensuring structural and temporal consistency over long sequences remains a challenge. Current methods predominantly rely on RGB signals, leading to accumulated errors in object structure and motion over extended durations. To address these issues, we introduce...","url_abs":"https://arxiv.org/abs/2508.15720","url_pdf":"https://arxiv.org/pdf/2508.15720v1","authors":"[\"Zhiheng Liu\",\"Xueqing Deng\",\"Shoufa Chen\",\"Angtian Wang\",\"Qiushan Guo\",\"Mingfei Han\",\"Zeyue Xue\",\"Mengzhao Chen\",\"Ping Luo\",\"Linjie Yang\"]","published":"2025-08-21T16:57:33Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}