Discrete-Continuous Transformation Matching for Dense Semantic Correspondence
- 주제(키워드) Semantics , Optimization , Strain , Computational modeling , Optical imaging , Labeling , Convolution , Dense semantic correspondence , discrete optimization , continuous optimization , interative inference
- 주제(기타) Computer Science, Artificial Intelligence; Engineering, Electrical & Electronic
- 설명문(일반) [Kim, Seungryong; Sohn, Kwanghoon] Yonsei Univ, Sch Elect & Elect Engn, Seoul 120749, South Korea; [Min, Dongbo] Ewha Womans Univ, Dept Comp Sci & Engn, Seoul 03760, South Korea; [Lin, Stephen] Microsoft Res, Beijing 100080, Peoples R China
- 관리정보기술 faculty
- 등재 SCIE, SCOPUS
- 발행기관 IEEE COMPUTER SOC
- 발행년도 2020
- 총서유형 Journal
- URI http://www.dcollection.net/handler/ewha/000000165909
- 본문언어 영어
- Published As http://dx.doi.org/10.1109/TPAMI.2018.2878240
- PubMed https://pubmed.ncbi.nlm.nih.gov/30371354
초록/요약
Techniques for dense semantic correspondence have provided limited ability to deal with the geometric variations that commonly exist between semantically similar images. While variations due to scale and rotation have been examined, there is a lack of practical solutions for more complex deformations such as affine transformations because of the tremendous size of the associated solution space. To address this problem, we present a discrete-continuous transformation matching (DCTM) framework where dense affine transformation fields are inferred through a discrete label optimization in which the labels are iteratively updated via continuous regularization. In this way, our approach draws solutions from the continuous space of affine transformations in a manner that can be computed efficiently through constant-time edge-aware filtering and a proposed affine-varying CNN-based descriptor. Furthermore, leveraging correspondence consistency and confidence-guided filtering in each iteration facilitates the convergence of our method. Experimental results show that this model outperforms the state-of-the-art methods for dense semantic correspondence on various benchmarks and applications.
more