纹理插值：纹理元匹配
Texture Interpolation as Texton Matching
AI总结：
该研究提出用感知外观的匹配替代位置配对，分离对应关系对纹理插值的影响，实验表明该方法可提升插值中点的分布质量，且对预训练模型也有效。
摘要：
纹理插值旨在探究两种纹理之间应存在何种内容。标准方法通常会在对应空间位置处混合像素或特征，隐含假设是共置元素应当被混合。然而对于不相关的纹理，这种对应关系是任意的：一幅图像中某位置的裂缝与另一幅图像相同位置的纤维并无特定关联。我们研究这种隐藏的配对选择本身是否是决定插值质量的主要因素。我们将纹理表示为局部外观向量（即纹理元）的集合，在保持编码器、表示和解码器固定的情况下，用感知外观的匹配替代位置配对。这将对应关系的影响与模型容量或训练的变化分离开来。在不同的纹理对上，感知外观的匹配始终比位置特征混合能提升插值中点的分布质量。软匹配产生最强的中点统计量，而一对一分配则产生更平衡的过渡，与目标端点的一致性更高。同样的干预措施在不重新训练的情况下也改进了第二个预训练纹理插值器。这些结果表明，对应关系是纹理插值中一个重要的设计选择：有意义的过渡不仅取决于两种纹理的混合强度，还取决于哪些局部外观相互混合。
英文摘要：
Texture interpolation asks what should lie between two textures. Standard methods typically blend pixels or features at corresponding spatial locations, implicitly assuming that co-located elements should be mixed. For unrelated textures, however, this correspondence is arbitrary: a crack at one location has no particular relationship to a fiber at the same location in another image. We study whether this hidden pairing choice is itself a major determinant of interpolation quality. We represent textures as collections of local appearance vectors, or textons, and replace positional pairing with appearance-aware matching while keeping the encoder, representation, and decoder fixed. This isolates the effect of correspondence from changes in model capacity or training. Across texture pairs, appearance-aware matching consistently improves the distributional quality of interpolated midpoints over positional feature blending. Soft matching produces the strongest midpoint statistics, whereas one-to-one assignments yield more balanced transitions and closer agreement with the target endpoint. The same intervention also improves a second pretrained texture interpolator without retraining. These results identify correspondence as a first-class design choice in texture interpolation: meaningful transitions depend not only on how strongly two textures are mixed, but also on which local appearances are mixed with one another.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
