ExPose：强化视频生成模型以实现极端姿态估计
ExPose: Reinforcing Video Generation Models for Extreme Pose Estimation
用 GRPO 偏好优化把视频生成模型的插帧结果对齐到 3D 一致的监督信号，可作为把生成式插帧当作数据增强/视角补全手段时消除空间不一致的通用做法。
原文依据 fine-tune a video generation model using Group Relative Preference Optimization (GRPO), aligning its outputs with 3D-consistent supervisory signals
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在稀疏视角下，姿态估计仍然具有挑战性，尤其是当图像之间的视觉重叠极其有限时。视频生成模型的最新进展提供了一种有前景的解决方案：通过关键帧插值来丰富上下文线索并提升姿态估计性能。然而，现有视频生成模型往往缺乏三维一致性，生成的帧在时序上看似合理，却在空间上不一致，从而损害下游的姿态估计。本文提出 ExPose 框架，直接解决在极端视角设定下将视频生成用于姿态估计时出现的三维不一致问题。具体而言，我们使用组相对偏好优化（GRPO）对视频生成模型进行微调，使其输出与由姿态估计目标导出的三维一致监督信号对齐。我们的方法不仅提升了时序插值的质量，还保证了跨视角的空间连贯性，从而显著提高姿态估计精度。大量实验表明，我们的方法优于最优基线，凸显了经偏好优化的视频生成作为极端视角场景下姿态估计有力工具的潜力。代码见 https://github.com/yh-yoon/ExPose。
英文原文摘要 1294 字符
Pose estimation remains challenging under sparse views, especially when visual overlap across images is extremely limited. Recent advances in video generation models offer a promising solution by enabling keyframe interpolation, which can enrich contextual cues and improve pose estimation performance. However, existing video generation models often lack 3D consistency, producing temporally plausible but spatially inconsistent frames that degrade downstream pose estimation. In this paper, we propose a framework ExPose that directly addresses 3D inconsistency when applying video generation to pose estimation in extreme-view settings. Specifically, we fine-tune a video generation model using Group Relative Preference Optimization (GRPO), aligning its outputs with 3D-consistent supervisory signals derived from pose estimation objectives. Our approach not only enhances the quality of temporal interpolation, but also ensures spatial coherence across views, significantly improving pose estimation accuracy. Extensive experiments demonstrate that our method outperforms state-of-the-art baselines, highlighting the potential of preference-optimized video generation as a powerful tool for pose estimation in extreme-view scenarios. Code is available at https://github.com/yh-yoon/ExPose.