{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fast-and-painless-image-reconstruction-in","title":"Image Reconstruction via Deep Image Prior Subspaces","arxiv_id":"2302.10279","date":"2023-02-20","proceeding":null,"authors":["Riccardo Barbano","Javier Antorán","Johannes Leuschner","José Miguel Hernández-Lobato","Bangti Jin","Željko Kereta"],"abstract":"Deep learning has been widely used for solving image reconstruction tasks but its deployability has been held back due to the shortage of high-quality training data. Unsupervised learning methods, such as the deep image prior (DIP), naturally fill this gap, but bring a host of new issues: the susceptibility to overfitting due to a lack of robust early stopping strategies and unstable convergence. We present a novel approach to tackle these issues by restricting DIP optimisation to a sparse linear subspace of its parameters, employing a synergy of dimensionality reduction techniques and second order optimisation methods. The low-dimensionality of the subspace reduces DIP's tendency to fit noise and allows the use of stable second order optimisation methods, e.g., natural gradient descent or L-BFGS. Experiments across both image restoration and tomographic tasks of different geometry and ill-posedness show that second order optimisation within a low-dimensional subspace is favourable in terms of optimisation stability to reconstruction fidelity trade-off.","url_abs":"https://arxiv.org/abs/2302.10279v2","url_pdf":"https://arxiv.org/pdf/2302.10279v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fast-and-painless-image-reconstruction-in","repo_url":"https://github.com/anonsubdip/subspace_dip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"image-restoration","task_name":"Image Restoration"}],"methods":[{"method_slug":"early-stopping","method_name":"Early Stopping"},{"method_slug":"natural-gradient-descent","method_name":"Natural Gradient Descent"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.10279","atlas_url":"https://app.syntology.ai/?focus=2302.10279","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}