English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We study the energy minimization problem in low-level vision tasks from anovel perspective. We replace the heuristic regularization term with alearnable subspace constraint, and preserve the data term to exploit domainknowledge derived from the first principle of a task. This learning subspaceminimization (LSM) framework unifies the network structures and the parametersfor many low-level vision tasks, which allows us to train a single network formultiple tasks simultaneously with completely shared parameters, and evengeneralizes the trained network to an unseen task as long as its data term canbe formulated. We demonstrate our LSM framework on four low-level tasksincluding interactive image segmentation, video segmentation, stereo matching,and optical flow, and validate the network on various datasets. The experimentsshow that the proposed LSM generates state-of-the-art results with smallermodel size, faster training convergence, and real-time inference.

LSM: Learning Subspace Minimization for Low-level Vision