论文标题

使用二级像素描述符的多尺度超级匹配匹配

Multi-Scale Superpatch Matching using Dual Superpixel Descriptors

论文作者

Giraud, Rémi, Boyer, Merlin, Clément, Michaël

论文摘要

超级像素的过度分割是一种非常有效的降维策略,从而实现了快速密集的图像处理。这种方法的主要问题是与标准层次多分辨率方案相比,图像分解的固有不规则性,尤其是在搜索相似的相邻模式时。几项作品试图通过考虑到其比较模型的区域不规则性来克服这一问题。然而,它们仍然是最佳的,可以提供可靠,准确的超像素邻域描述符,因为它们仅计算每个区域内的特征,在超像素边框处捕获了轮廓信息。在这项工作中,我们通过引入新颖的Superpixel邻里描述符Dual SuperPatch来解决这些局限性。该结构包含在简化的超像素区域以及多个超级像素的界面中计算出的特征,以明确捕获轮廓结构信息。还引入了快速的多尺度非本地匹配框架,以搜索图像数据集中不同分辨率级别的类似描述符。所提出的双重键入使得在不同尺度上更准确地捕获相似的结构化模式,我们证明了这种新策略在匹配和监督标签应用程序中的稳健性和性能。

Over-segmentation into superpixels is a very effective dimensionality reduction strategy, enabling fast dense image processing. The main issue of this approach is the inherent irregularity of the image decomposition compared to standard hierarchical multi-resolution schemes, especially when searching for similar neighboring patterns. Several works have attempted to overcome this issue by taking into account the region irregularity into their comparison model. Nevertheless, they remain sub-optimal to provide robust and accurate superpixel neighborhood descriptors, since they only compute features within each region, poorly capturing contour information at superpixel borders. In this work, we address these limitations by introducing the dual superpatch, a novel superpixel neighborhood descriptor. This structure contains features computed in reduced superpixel regions, as well as at the interfaces of multiple superpixels to explicitly capture contour structure information. A fast multi-scale non-local matching framework is also introduced for the search of similar descriptors at different resolution levels in an image dataset. The proposed dual superpatch enables to more accurately capture similar structured patterns at different scales, and we demonstrate the robustness and performance of this new strategy on matching and supervised labeling applications.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源