{"ID":5443868,"CreatedAt":"2026-07-01T02:07:11.383974684Z","UpdatedAt":"2026-07-07T01:54:07.268702664Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31959","arxiv_id":"2606.31959","title":"AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer","abstract":"Depth-of-field control is a fundamental tool in photography, yet post-capture bokeh editing from a single image remains challenging. A practical editor should handle images captured under arbitrary focus and aperture settings. Existing methods typically assume an all-in-focus input, or first recover an all-in-focus image before rendering new bokeh. Such pipelines can discard useful blur cues from the source image and propagate reconstruction artifacts into the final edit. We introduce AnyBokeh, a physics-guided framework for any-to-any bokeh editing. Instead of treating source blur merely as a degradation to be removed, AnyBokeh estimates the source blur state with a signed circle-of-confusion map and a disparity map. By modeling the linear relation between signed circle of confusion and disparity difference, AnyBokeh estimates a source-specific optical fingerprint and transfers the source optical characteristics to the desired focus and aperture setting. A generative editor conditioned on both source and target circle-of-confusion maps then performs relative blur synthesis, enabling spatially adaptive deblurring, preservation, and defocus rendering. To support physically supervised learning, we further construct a high-fidelity synthetic dataset with accurate depth, focus distance, and full EXIF metadata. Experiments on real-world benchmarks show that AnyBokeh achieves faithful and controllable editing across any-to-any bokeh editing, all-in-focus-to-bokeh rendering, and defocus deblurring, while avoiding all-in-focus reconstruction and test-time bokeh-level calibration commonly required by existing approaches. The code and dataset will be available at https://github.com/itsmag11/AnyBokeh.","short_abstract":"Depth-of-field control is a fundamental tool in photography, yet post-capture bokeh editing from a single image remains challenging. A practical editor should handle images captured under arbitrary focus and aperture settings. Existing methods typically assume an all-in-focus input, or first recover an all-in-focus ima...","url_abs":"https://arxiv.org/abs/2606.31959","url_pdf":"https://arxiv.org/pdf/2606.31959v1","authors":"[\"Xinyu Hou\",\"Xiaoming Li\",\"Zongsheng Yue\",\"Chen Change Loy\"]","published":"2026-06-30T17:01:28Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":613817,"CreatedAt":"2026-07-01T02:07:11.383974684Z","UpdatedAt":"2026-07-01T02:07:11.383974684Z","DeletedAt":null,"paper_id":5443868,"paper_url":"https://arxiv.org/abs/2606.31959","paper_title":"AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer","repo_url":"https://github.com/itsmag11/AnyBokeh","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}