Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework

2026-05-08

AI Summary

This work addresses the challenge of generating high-quality bokeh effects on mobile devices under high digital zoom, where optical limitations and low-resolution inputs often lead to detail loss and computational inefficiency in existing methods. To overcome these issues, the authors propose MagicBokeh, a unified diffusion-based framework that jointly optimizes bokeh rendering and super-resolution. The approach introduces a focus-aware mask attention mechanism and a degradation-aware depth estimation module, trained end-to-end to efficiently produce photorealistic bokeh images directly from low-resolution inputs. Experimental results demonstrate that MagicBokeh significantly outperforms current state-of-the-art methods in visual fidelity, depth estimation accuracy, and user controllability, thereby advancing the state of mobile bokeh rendering.

Abstract

Existing mobile devices are constrained by compact optical designs, such as small apertures, which make it difficult to produce natural, optically realistic bokeh effects. Although recent learning-based methods have shown promising results, they still struggle with photos captured under high digital zoom levels, which often suffer from reduced resolution and loss of fine details. A naive solution is to enhance image quality before applying bokeh rendering, yet this two-stage pipeline reduces efficiency and introduces unnecessary error accumulation. To overcome these limitations, we propose MagicBokeh, a unified diffusion-based framework designed for high-quality and efficient bokeh rendering. Through an alternative training strategy and a focus-aware masked attention mechanism, our method jointly optimizes bokeh rendering and super-resolution, substantially improving both controllability and visual fidelity. Furthermore, we introduce degradation-aware depth module to enable more accurate depth estimation from low-quality inputs. Experimental results demonstrate that MagicBokeh efficiently produces photorealistic bokeh effects, particularly on real-world low-resolution images, paving the way for future advancements in bokeh rendering. Our code and models are available at https://github.com/vivoCameraResearch/MagicBokeh.

Problem

• bokeh rendering
• mobile photography
• low-resolution images
• digital zoom
• photorealistic effects

Innovation

• diffusion framework
• bokeh rendering
• super-resolution
• masked attention
• degradation-aware depth estimation