all AI news
Strong and Controllable Blind Image Decomposition
March 18, 2024, 4:42 a.m. | Zeyu Zhang, Junlin Han, Chenhui Gou, Hongdong Li, Liang Zheng
cs.LG updates on arXiv.org arxiv.org
Abstract: Blind image decomposition aims to decompose all components present in an image, typically used to restore a multi-degraded input image. While fully recovering the clean image is appealing, in some scenarios, users might want to retain certain degradations, such as watermarks, for copyright protection. To address this need, we add controllability to the blind image decomposition process, allowing users to enter which types of degradation to remove or retain. We design an architecture named controllable …
abstract arxiv blind components copyright copyright protection cs.cv cs.lg eess.iv image protection restore type watermarks
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote