全光视频生成
Plenoptic Video Generation
把「多进单出」的视频条件模型以自回归方式串起来，并用相机引导的视频检索从历史生成中挑显著帧做条件，这套「时空记忆+检索式条件」可直接迁移到任何需要跨视角/跨时序一致性的生成式重渲染或长视频生成任务。
原文依据 train a multi-in-single-out video-conditioned model in an autoregressive manner, aided by a camera-guided video retrieval strategy
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论相机控制的生成式视频重渲染方法（如 ReCamMaster）已取得显著进展。然而，尽管这些工作在单视角设定下取得了成功，它们往往难以在多视角场景中保持一致性。由于生成模型固有的随机性，确保幻觉区域中的时空连贯性仍然具有挑战性。为解决该问题，我们提出 PlenopticDreamer，一个同步生成式幻觉以维持时空记忆的框架。其核心思想是以自回归方式训练一个多输入单输出的视频条件模型，并辅以相机引导的视频检索策略，该策略自适应地从先前生成结果中选取显著视频作为条件输入。此外，我们的训练引入了渐进式上下文缩放以改善收敛，引入自条件以增强对误差累积所导致的长程视觉退化的鲁棒性，并引入长视频条件机制以支持扩展视频生成。在 Basic 与 Agibot 基准上的大量实验表明，PlenopticDreamer 实现了最优的视频重渲染，提供更优的视角同步、高保真视觉、准确的相机估计以及多样的视角变换（例如第三人称到第三人称，以及机器人操作中的头部视角到夹爪视角）。
英文原文摘要 1390 字符
Camera-controlled generative video re-rendering methods, such as ReCamMaster, have achieved remarkable progress. However, despite their success in single-view setting, these works often struggle to maintain consistency across multi-view scenarios. Ensuring spatio-temporal coherence in hallucinated regions remains challenging due to the inherent stochasticity of generative models. To address it, we introduce PlenopticDreamer, a framework that synchronizes generative hallucinations to maintain spatio-temporal memory. The core idea is to train a multi-in-single-out video-conditioned model in an autoregressive manner, aided by a camera-guided video retrieval strategy that adaptively selects salient videos from previous generations as conditional inputs. In addition, Our training incorporates progressive context-scaling to improve convergence, self-conditioning to enhance robustness against long-range visual degradation caused by error accumulation, and a long-video conditioning mechanism to support extended video generation. Extensive experiments on the Basic and Agibot benchmarks demonstrate that PlenopticDreamer achieves state-of-the-art video re-rendering, delivering superior view synchronization, high-fidelity visuals, accurate camera estimation, and diverse view transformations (e.g., third-person - third-person, and head-view - gripper-view in robotic manipulation).