{"url":"/method/irn","slug":"irn","name":"IRN","full_name":"Invertible Rescaling Network","full_name_withheld":false,"description_markdown":"An **Invertible Rescaling Network (IRN)** is a network for image rescaling.  According to the Nyquist-Shannon sampling theorem, high-frequency contents are lost during downscaling. Ideally, we hope to keep all lost information to perfectly recover the original HR image, but storing or transferring the high-frequency information is unacceptable. In order to well address this challenge, the Invertible Rescaling Net (IRN) captures some knowledge on the lost information in the form of its distribution and embeds it into model’s parameters to mitigate the ill-posedness. Given an HR image $x$, IRN not only downscales it into a LR image y, but also embeds the case-specific high-frequency content into an auxiliary case-agnostic latent variable $z$, whose marginal distribution\r\nobeys a fixed pre-specified distribution (e.g., isotropic Gaussian). Based on this model,\r\nwe use a randomly drawn sample of $z$ from the pre-specified distribution for the inverse upscaling procedure, which holds the most information that one could have in upscaling.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/2005.05650v1","title":"Invertible Image Rescaling","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/pkuxmq/Invertible-Image-Rescaling/blob/f74e8442bdd9d9064bae962267cc29546c4943b9/codes/models/IRN_model.py#L15","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Image Models","url":"/methods/category/image-models","pwc_aliases":[]}],"n_papers_tagged":6,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"title":"Invertible Residual Rescaling Models","date":"2024-05-05","arxiv_id":"2405.02945","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-ai-systems-under-uncertain-ground","title":"Evaluating AI systems under uncertain ground truth: a case study in dermatology","date":"2023-07-05","arxiv_id":"2307.02191","n_code_links":1,"syntology":null},{"paper":null,"title":"Raising The Limit Of Image Rescaling Using Auxiliary Encoding","date":"2023-03-12","arxiv_id":"2303.06747","n_code_links":0,"syntology":null},{"paper":null,"title":"Influential Recommender System","date":"2022-11-18","arxiv_id":"2211.10002","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-image-rescaling-using-dual-latent","title":"Enhancing Image Rescaling using Dual Latent Variables in Invertible Neural Network","date":"2022-07-24","arxiv_id":"2207.11844","n_code_links":1,"syntology":null},{"paper":"/paper/invertible-image-rescaling","title":"Invertible Image Rescaling","date":"2020-05-12","arxiv_id":"2005.05650","n_code_links":11,"syntology":{"ran":3,"of":17,"unverified":14,"pointer_only":0}}],"papers_shown":6,"tasks":[{"task":"/task/image-rescaling","name":"Image Rescaling","papers":4},{"task":"/task/image-super-resolution","name":"Image Super-Resolution","papers":3},{"task":"/task/super-resolution","name":"Super-Resolution","papers":3},{"task":"/task/diagnostic","name":"Diagnostic","papers":1},{"task":"/task/image-restoration","name":"Image Restoration","papers":1},{"task":"/task/medical-diagnosis","name":"Medical Diagnosis","papers":1},{"task":"/task/recommendation-systems","name":"Recommendation Systems","papers":1}],"tasks_shown":7,"n_tasks":7,"usage_by_year":[{"year":"2020","papers":1},{"year":"2022","papers":2},{"year":"2023","papers":2},{"year":"2024","papers":1}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/irn"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}