TY - GEN
T1 - Harmonious semantic line detection via maximal weight clique selection
AU - Jin, Dongkwon
AU - Park, Wonhui
AU - Jeong, Seong Gyun
AU - Kim, Chang Su
N1 - Funding Information:
This work was supported in part by the National Research Foundation of Korea (NRF) through the Korea Government (MSIT) under grant NRF-2018R1A2B3003896 and in part by the 42dot Inc.
Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - A novel algorithm to detect an optimal set of semantic lines is proposed in this work. We develop two networks: selection network (S-Net) and harmonization network (H-Net). First, S-Net computes the probabilities and offsets of line candidates. Second, we filter out irrelevant lines through a selection-and-removal process. Third, we construct a complete graph, whose edge weights are computed by H-Net. Finally, we determine a maximal weight clique representing an optimal set of semantic lines. Moreover, to assess the overall harmony of detected lines, we propose a novel metric, called HIoU. Experimental results demonstrate that the proposed algorithm can detect harmonious semantic lines effectively and efficiently. Our codes are available at https://github.com/dongkwonjin/Semantic-Line-MWCS.
AB - A novel algorithm to detect an optimal set of semantic lines is proposed in this work. We develop two networks: selection network (S-Net) and harmonization network (H-Net). First, S-Net computes the probabilities and offsets of line candidates. Second, we filter out irrelevant lines through a selection-and-removal process. Third, we construct a complete graph, whose edge weights are computed by H-Net. Finally, we determine a maximal weight clique representing an optimal set of semantic lines. Moreover, to assess the overall harmony of detected lines, we propose a novel metric, called HIoU. Experimental results demonstrate that the proposed algorithm can detect harmonious semantic lines effectively and efficiently. Our codes are available at https://github.com/dongkwonjin/Semantic-Line-MWCS.
UR - http://www.scopus.com/inward/record.url?scp=85124198267&partnerID=8YFLogxK
U2 - 10.1109/CVPR46437.2021.01646
DO - 10.1109/CVPR46437.2021.01646
M3 - Conference contribution
AN - SCOPUS:85124198267
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 16732
EP - 16740
BT - Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
PB - IEEE Computer Society
T2 - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
Y2 - 19 June 2021 through 25 June 2021
ER -