发表机构
Reichman University（雷赫曼大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对镜面修复问题，提出一种无需训练的几何约束双掩码扩散策略，通过估计场景几何并投影可见内容到镜面，结合生成模型平衡几何约束与先验，在MirrorBench-V2等数据集上提升了反射一致性。
AI 中文摘要
镜子是真实图像中的常见元素，但用生成模型生成几何一致的反射仍具挑战性。与多数物体不同，镜面外观依赖场景几何与视角，仅靠学习到的外观先验难以合成。本文针对镜面修复场景展开研究，该场景中场景固定，仅需生成镜面区域。核心见解是：大量镜面内容受可见场景的几何约束，无需凭空生成。我们估计场景几何并将可见内容投影到镜面，以恢复由几何决定的反射区域，随后生成模型通过双掩码扩散策略完成镜面区域，该策略平衡几何约束与模型学习到的先验，减少投影伪影并提升反射一致性。该方法无需训练，适用于复杂真实场景，我们在MirrorBench-V2（合成数据）和真实图像上进行评估，使用标准及几何感知指标，结果表明显式利用场景几何可提升一致性。
英文摘要
Mirrors are common in real-world images, yet producing geometrically consistent reflections with generative models remains challenging. Unlike most objects, mirror appearance depends on scene geometry and viewpoint, making it hard to synthesize using learned appearance priors alone. We address this in the mirror inpainting setting, where the scene is fixed and only the mirror region is generated. Our key insight is that much mirror content is geometrically constrained by the visible scene and need not be hallucinated. We estimate scene geometry and project visible content into the mirror to recover reflection regions determined by geometry. A generative model then completes the mirror region via a two-mask diffusion strategy balancing geometric constraints with the model's learned priors, reducing projection artifacts and improving reflection consistency. The method is training-free and applicable to complex real-world scenes. We evaluate on MirrorBench-V2 (synthetic) and real images. Using standard and geometry-aware metrics, we show that explicitly using scene geometry improves consistency.
