KAUST DepartmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Computer Science Program
Visual Computing Center (VCC)
MetadataShow full item record
AbstractRecently, several discriminative learning approaches have been proposed for effective image restoration, achieving convincing trade-off between image quality and computational efficiency. However, these methods require separate training for each restoration task (e.g., denoising, deblurring, demosaicing) and problem condition (e.g., noise level of input images). This makes it time-consuming and difficult to encompass all tasks and conditions during training. In this paper, we propose a discriminative transfer learning method that incorporates formal proximal optimization and discriminative learning for general image restoration. The method requires a single-pass discriminative training and allows for reuse across various problems and conditions while achieving an efficiency comparable to previous discriminative approaches. Furthermore, after being trained, our model can be easily transferred to new likelihood terms to solve untrained tasks, or be combined with existing priors to further improve image restoration quality.
CitationXiao L, Heide F, Heidrich W, Schölkopf B, Hirsch M (2018) Discriminative Transfer Learning for General Image Restoration. IEEE Transactions on Image Processing 27: 4091–4104. Available: http://dx.doi.org/10.1109/TIP.2018.2831925.
SponsorsThis work was in part supported by King Abdullah University of Science and Technology under individual baseline funding. The associate editor coordinating the review of this manuscript and approving it for publication was Prof. Weisi Lin.