EgoX：从单段第三人称视频生成第一人称视频
EgoX: Egocentric Video Generation from a Single Exocentric Video
将大规模视频扩散模型通过轻量低秩适配迁移到极端视角变换的跨视角视频生成任务，其宽度/通道拼接的条件注入策略与几何引导自注意力机制可复用于新视角合成、视角转换等需要保持几何一致性的生成任务。
原文依据 a geometry-guided self-attention mechanism selectively attends to spatially relevant regions, ensuring geometric coherence
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论第一人称感知使人类能够直接从自身视角体验和理解世界。将第三人称视频转换为第一人称视频为沉浸式理解开辟了新的可能性，但由于极端的相机位姿变化和极小的视角重叠，这一任务仍极具挑战性。该任务要求在忠实保留可见内容的同时，以几何一致的方式合成未见区域。为实现这一目标，我们提出 EgoX，一个从单段第三人称输入生成第一人称视频的新框架。EgoX 通过轻量级低秩适配利用大规模视频扩散模型预训练的时空知识，并引入一种统一的条件策略，通过宽度维度和通道维度的拼接将第三人称与第一人称先验相结合。此外，几何引导的自注意力机制选择性地关注空间相关区域，从而确保几何一致性和高视觉保真度。我们的方法实现了连贯且逼真的第一人称视频生成，同时在未见视频和野外视频上展现出强大的可扩展性与鲁棒性。
英文原文摘要 1185 字符
Egocentric perception enables humans to experience and understand the world directly from their own point of view. Translating exocentric (third-person) videos into egocentric (first-person) videos opens up new possibilities for immersive understanding but remains highly challenging due to extreme camera pose variations and minimal view overlap. This task requires faithfully preserving visible content while synthesizing unseen regions in a geometrically consistent manner. To achieve this, we present EgoX, a novel framework for generating egocentric videos from a single exocentric input.EgoX leverages the pretrained spatio-temporal knowledge of large-scale video diffusion models through lightweight LoRA adaptation and introduces a unified conditioning strategy that combines exocentric and egocentric priors via width- and channel-wise concatenation.Additionally, a geometry-guided self-attention mechanism selectively attends to spatially relevant regions, ensuring geometric coherence and high visual fidelity.Our approach achieves coherent and realistic egocentric video generation while demonstrating strong scalability and robustness across unseen and in-the-wild videos.