References & Citations
Computer Science > Computer Vision and Pattern Recognition
Title: S3R-Net: A Single-Stage Approach to Self-Supervised Shadow Removal
(Submitted on 18 Apr 2024)
Abstract: In this paper we present S3R-Net, the Self-Supervised Shadow Removal Network. The two-branch WGAN model achieves self-supervision relying on the unify-and-adaptphenomenon - it unifies the style of the output data and infers its characteristics from a database of unaligned shadow-free reference images. This approach stands in contrast to the large body of supervised frameworks. S3R-Net also differentiates itself from the few existing self-supervised models operating in a cycle-consistent manner, as it is a non-cyclic, unidirectional solution. The proposed framework achieves comparable numerical scores to recent selfsupervised shadow removal models while exhibiting superior qualitative performance and keeping the computational cost low.
Submission history
From: Nikolina Kubiak [view email][v1] Thu, 18 Apr 2024 11:36:37 GMT (10131kb,D)
Link back to: arXiv, form interface, contact.