Paper page - AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer

Source: https://huggingface.co/papers/2606.31959

Abstract

AnyBokeh is a physics-guided framework for bokeh editing that estimates source blur states and transfers optical characteristics between different focus and aperture settings without requiring all-in-focus reconstruction.

Depth-of-field control is a fundamental tool in photography, yet post-capturebokeh editingfrom 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-anybokeh editing. Instead of treating source blur merely as a degradation to be removed, AnyBokeh estimates the source blur state with a signedcircle-of-confusion mapand adisparity map. By modeling the linear relation between signed circle of confusion and disparity difference, AnyBokeh estimates a source-specificoptical fingerprintand transfers the source optical characteristics to the desired focus and aperture setting. Agenerative editorconditioned on both source and targetcircle-of-confusion maps then performsrelative blur synthesis, enabling spatially adaptive deblurring, preservation, and defocus rendering. To support physically supervised learning, we further construct a high-fidelitysynthetic datasetwith accurate depth, focus distance, and fullEXIF metadata. Experiments on real-world benchmarks show that AnyBokeh achieves faithful and controllable editing across any-to-anybokeh 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.

View arXiv pageView PDFGitHubAdd to collection

Get this paper in your agent:

hf papers read 2606\.31959

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.31959 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.31959 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.31959 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.