{"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/deep-network-interpolation-for-continuous","title":"Deep Network Interpolation for Continuous Imagery Effect Transition","arxiv_id":"1811.10515","date":"2018-11-26","proceeding":"CVPR 2019 6","authors":["Xintao Wang","Ke Yu","Chao Dong","Xiaoou Tang","Chen Change Loy"],"abstract":"Deep convolutional neural network has demonstrated its capability of learning\na deterministic mapping for the desired imagery effect. However, the large\nvariety of user flavors motivates the possibility of continuous transition\namong different output effects. Unlike existing methods that require a specific\ndesign to achieve one particular transition (e.g., style transfer), we propose\na simple yet universal approach to attain a smooth control of diverse imagery\neffects in many low-level vision tasks, including image restoration,\nimage-to-image translation, and style transfer. Specifically, our method,\nnamely Deep Network Interpolation (DNI), applies linear interpolation in the\nparameter space of two or more correlated networks. A smooth control of imagery\neffects can be achieved by tweaking the interpolation coefficients. In addition\nto DNI and its broad applications, we also investigate the mechanism of network\ninterpolation from the perspective of learned filters.","url_abs":"http://arxiv.org/abs/1811.10515v1","url_pdf":"http://arxiv.org/pdf/1811.10515v1.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":"deep-network-interpolation-for-continuous","repo_url":"https://github.com/kzkymur/transition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-network-interpolation-for-continuous","repo_url":"https://github.com/S-aiueo32/dni-demo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"style-transfer","task_name":"Style Transfer"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"tunable-network","method_name":"Tunable Network"}],"datasets_introduced":[],"methods_introduced":[{"slug":"tunable-network","name":"Tunable Network","full_name":"Tunable Network"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.10515","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}