English

Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework

Computer Vision and Pattern Recognition 2026-05-12 v2

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.

Keywords

Cite

@article{arxiv.2605.07429,
  title  = {Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework},
  author = {Linxiao Shi and Siming Zheng and Zerong Wang and Hao Zhang and Jinwei Chen and Bo Li and Shifeng Chen and Peng-Tao Jiang},
  journal= {arXiv preprint arXiv:2605.07429},
  year   = {2026}
}

Comments

Accepted by CVPR 2026

R2 v1 2026-07-01T12:57:13.065Z