We present a novel means of describing local image appearances using binary strings. Binary descriptors have drawn increasing interest in recent years due to their speed and low memory footprint. A known shortcoming of these representations is their inferior performance compared to larger, histogram based descriptors such as the SIFT. Our goal is to close this performance gap while maintaining the benefits attributed to binary representations. To this end we propose the Learned Arrangements of Three Patch Codes descriptors, or LATCH. Our key observation is that existing binary descriptors are at an increased risk from noise and local appearance variations. This, as they compare the values of pixel pairs; changes to either of the pixels can easily lead to changes in descriptor values, hence damaging its performance. In order to provide more robustness, we instead propose a novel means of comparing pixel patches. This ostensibly small change, requires a substantial redesign of the descriptors themselves and how they are produced. Our resulting LATCH representation is rigorously compared to state-of-the-art binary descriptors and shown to provide far better performance for similar computation and space requirements.

提出了 Learned Arrangements of Three Patch Codes descriptors (LATCH) 的方法，通过使用像素块的新颖比较方法，着眼于解决现有二进制描述符在处理噪声和局部外观变化时的性能问题，相比其他二进制描述符具有更好的性能表现。

LATCH: 三补丁码的学习排列