swMATH ID: 32735
Software Authors: Chambolle, A.; Holler, M.; Pock, T.
Description: A convex variational model for learning convolutional image atoms from incomplete data. A variational model for learning convolutional image atoms from corrupted and/or incomplete data is introduced and analyzed both in function space and numerically. Building on lifting and relaxation strategies, the proposed approach is convex and allows for simultaneous image reconstruction and atom learning in a general, inverse problems context. Further, motivated by an improved numerical performance, also a semi-convex variant is included in the analysis and the experiments of the paper. For both settings, fundamental analytical properties allowing in particular to ensure well-posedness and stability results for inverse problems are proven in a continuous setting. Exploiting convexity, globally optimal solutions are further computed numerically for applications with incomplete, noisy and blurry data and numerical results are shown.
Homepage: https://link.springer.com/article/10.1007/s10851-019-00919-7
Source Code:  https://github.com/hollerm/convex_learning
Keywords: variational methods; learning approaches; inverse problems; functional lifting; convex relaxation; convolutional Lasso; machine learning; texture reconstruction
Related Software: GitHub; DeepAdverserialRegulariser; TensorFlow; compsensing_dip; NETT; PyTorch; ODL; Adam; PyOpenCL; PyCUDA; PDCO; BM3D; SPORCO; Wasserstein GAN; DGM; VoxelMorph; Quicksilver; PDE-Net; BUQO; U-Net
Cited in: 5 Documents

Citations by Year