TY - GEN
T1 - Sublabel-Accurate Discretization of Nonconvex Free-Discontinuity Problems
AU - Mollenhoff, Thomas
AU - Cremers, Daniel
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/12/22
Y1 - 2017/12/22
N2 - In this work we show how sublabel-accurate multilabeling approaches [15, 18] can be derived by approximating a classical label-continuous convex relaxation of nonconvex free-discontinuity problems. This insight allows to extend these sublabel-accurate approaches from total variation to general convex and nonconvex regularizations. Furthermore, it leads to a systematic approach to the discretization of continuous convex relaxations. We study the relationship to existing discretizations and to discrete-continuous MRFs. Finally, we apply the proposed approach to obtain a sublabel-accurate and convex solution to the vectorial Mumford-Shah functional and show in several experiments that it leads to more precise solutions using fewer labels.
AB - In this work we show how sublabel-accurate multilabeling approaches [15, 18] can be derived by approximating a classical label-continuous convex relaxation of nonconvex free-discontinuity problems. This insight allows to extend these sublabel-accurate approaches from total variation to general convex and nonconvex regularizations. Furthermore, it leads to a systematic approach to the discretization of continuous convex relaxations. We study the relationship to existing discretizations and to discrete-continuous MRFs. Finally, we apply the proposed approach to obtain a sublabel-accurate and convex solution to the vectorial Mumford-Shah functional and show in several experiments that it leads to more precise solutions using fewer labels.
UR - http://www.scopus.com/inward/record.url?scp=85041892872&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2017.134
DO - 10.1109/ICCV.2017.134
M3 - Conference contribution
AN - SCOPUS:85041892872
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 1192
EP - 1200
BT - Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 16th IEEE International Conference on Computer Vision, ICCV 2017
Y2 - 22 October 2017 through 29 October 2017
ER -