StereoWorld：几何感知的单目到立体视频生成
StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation
把预训练视频生成器改造成单目到立体的生成器，并用几何感知正则化显式约束视差结构，对做视频生成、立体内容生产、以及想在生成过程中注入3D几何先验的人可直接复用。
原文依据 explicitly supervising the generation with a geometry-aware regularization to ensure 3D structural fidelity
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论XR 设备的日益普及带动了对高质量立体视频的强烈需求，但其制作成本高昂且容易出现伪影。为应对这一挑战，本文提出 StereoWorld，一个端到端框架，将预训练视频生成器改造用于高保真单目到立体视频生成。该框架在联合以单目视频输入为条件的同时，用几何感知正则化对生成过程进行显式监督，以确保三维结构保真度。进一步集成时空分块方案，以实现高效的高分辨率合成。为支持大规模训练与评测，我们构建了一个高清立体视频数据集，包含超过 1100 万帧，且对齐自然人类瞳距（IPD）。大量实验表明，StereoWorld 显著优于先前方法，生成的立体视频具有更优的视觉保真度与几何一致性。
英文原文摘要 974 字符
The growing adoption of XR devices has fueled strong demand for high-quality stereo video, yet its production remains costly and artifact-prone.To address this challenge, we present **StereoWorld**, an **end-to-end framework** that repurposes a pretrained video generator for high-fidelity monocular-to-stereo video generation. Our framework jointly conditions the model on the monocular video input while explicitly supervising the generation with a **geometry-aware regularization** to ensure 3D structural fidelity.A spatio-temporal tiling scheme is further integrated to enable efficient, high-resolution synthesis.To enable large-scale training and evaluation, we curate a **high-definition stereo video dataset** containing over 11M frames aligned to natural human interpupillary distance (IPD).Extensive experiments demonstrate that StereoWorld substantially outperforms prior methods, generating stereo videos with superior visual fidelity and geometric consistency.