BokehFlow: Depth-Free Controllable Bokeh Rendering via Flow Matching

TL;DR

BokehFlow is a novel depth-free framework that synthesizes controllable, photorealistic bokeh effects from all-in-focus images using flow matching and semantic control, eliminating the need for depth maps.

Contribution

It introduces a depth-free, flow matching-based approach with semantic control for photorealistic bokeh rendering, surpassing existing methods in quality and efficiency.

Findings

Outperforms depth-dependent methods in visual quality

Provides precise semantic control via text prompts

Achieves efficient real-time bokeh synthesis

Abstract

Bokeh rendering simulates the shallow depth-of-field effect in photography, enhancing visual aesthetics and guiding viewer attention to regions of interest. Although recent approaches perform well, rendering controllable bokeh without additional depth inputs remains a significant challenge. Existing classical and neural controllable methods rely on accurate depth maps, while generative approaches often struggle with limited controllability and efficiency. In this paper, we propose BokehFlow, a depth-free framework for controllable bokeh rendering based on flow matching. BokehFlow directly synthesizes photorealistic bokeh effects from all-in-focus images, eliminating the need for depth inputs. It employs a cross-attention mechanism to enable semantic control over both focus regions and blur intensity via text prompts. To support training and evaluation, we collect and synthesize four datasets. Extensive experiments demonstrate that BokehFlow achieves visually compelling bokeh effects and offers precise control, outperforming existing depth-dependent and generative methods in both rendering quality and efficiency.