DASC: Robust Dense Descriptor for Multi-Modal and Multi-Spectral Correspondence Estimation
- 주제(키워드) Dense correspondence , descriptor , multi-spectral , multi-modal , edge-aware filtering
- 주제(기타) Computer Science, Artificial Intelligence
- 주제(기타) Engineering, Electrical & Electronic
- 관리정보기술 faculty
- 등재 SCIE, SCOPUS
- 발행기관 IEEE COMPUTER SOC
- 발행년도 2017
- 총서유형 Journal
- URI http://www.dcollection.net/handler/ewha/000000162134
- 본문언어 영어
- Published As http://dx.doi.org/10.1109/TPAMI.2016.2615619
초록/요약
Establishing dense correspondences between multiple images is a fundamental task in many applications. However, finding a reliable correspondence between multi-modal or multi-spectral images still remains unsolved due to their challenging photometric and geometric variations. In this paper, we propose a novel dense descriptor, called dense adaptive self-correlation (DASC), to estimate dense multi-modal and multi-spectral correspondences. Based on an observation that self-similarity existing within images is robust to imaging modality variations, we define the descriptor with a series of an adaptive self-correlation similarity measure between patches sampled by a randomized receptive field pooling, in which a sampling pattern is obtained using a discriminative learning. The computational redundancy of dense descriptors is dramatically reduced by applying fast edge-aware filtering. Furthermore, in order to address geometric variations including scale and rotation, we propose a geometry-invariant DASC (GI-DASC) descriptor that effectively leverages the DASC through a superpixel-based representation. For a quantitative evaluation of the GI-DASC, we build a novel multi-modal benchmark as varying photometric and geometric conditions. Experimental results demonstrate the outstanding performance of the DASC and GI-DASC in many cases of dense multi-modal and multi-spectral correspondences.
more