Bokehlicious: Photorealistic Bokeh Rendering with Controllable Apertures

2025-03-20

AI Summary

Existing Bokeh rendering methods rely on synthetic data, resulting in poor perceptual realism, imprecise blur intensity control, and dependence on auxiliary inputs. To address these limitations, we propose a photorealistic, controllable Bokeh rendering framework. First, we introduce an aperture-aware attention mechanism that physically models lens aperture dynamics to enable continuous, interpretable blur intensity control. Second, we construct RealBokeh—the first large-scale, 24-megapixel real-captured professional dataset (23,000 images) grounded entirely in physical optics. Third, we design a lightweight neural architecture with zero-shot generalization capability, enabling end-to-end training directly on real imagery. Our method achieves state-of-the-art performance on RealBokeh and established benchmarks, with significantly accelerated inference. Furthermore, we extend our framework to defocus deblurring, attaining competitive results on RealDOF.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Search and Optimization: Sampling/Simulation-based Search
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Bokeh rendering methods play a key role in creating the visually appealing, softly blurred backgrounds seen in professional photography. While recent learning-based approaches show promising results, generating realistic Bokeh with variable strength remains challenging. Existing methods require additional inputs and suffer from unrealistic Bokeh reproduction due to reliance on synthetic data. In this work, we propose Bokehlicious, a highly efficient network that provides intuitive control over Bokeh strength through an Aperture-Aware Attention mechanism, mimicking the physical lens aperture. To further address the lack of high-quality real-world data, we present RealBokeh, a novel dataset featuring 23,000 high-resolution (24-MP) images captured by professional photographers, covering diverse scenes with varied aperture and focal length settings. Evaluations on both our new RealBokeh and established Bokeh rendering benchmarks show that Bokehlicious consistently outperforms SOTA methods while significantly reducing computational cost and exhibiting strong zero-shot generalization. Our method and dataset further extend to defocus deblurring, achieving competitive results on the RealDOF benchmark. Our code and data can be found at https://github.com/TimSeizinger/Bokehlicious

Problem

• Realistic Bokeh rendering with variable strength control
• Overcoming reliance on synthetic data for Bokeh reproduction
• Lack of high-quality real-world Bokeh datasets

Innovation

• Aperture-Aware Attention mechanism for Bokeh control
• RealBokeh dataset with 23,000 high-resolution images
• Efficient network reducing computational cost significantly