Showing 2025Show all
2 papers · 1 filter
cs.CV2025
Unrolling Graph-based Douglas-Rachford Algorithm for Image Interpolation with Informed Initialization
Xue Zhang, Bingshuo Hu, Gene Cheung
Conventional deep neural nets (DNNs) initialize network parameters at random and then optimize each one via stochastic gradient descent (SGD), resulting in substantial risk of poor…
eess.IV2025
Unrolling Nonconvex Graph Total Variation for Image Denoising
Songlin Wei, Gene Cheung, Fei Chen +1
Conventional model-based image denoising optimizations employ convex regularization terms, such as total variation (TV) that convexifies the -norm to promote sparse signal…