Bokeh-Loss GAN: Multi-Stage Adversarial Training for Realistic Edge-Aware Bokeh
This addresses the problem of simulating DSLR-like bokeh effects for mobile camera users, representing an incremental improvement in image processing.
The paper tackles monocular bokeh synthesis from single all-in-focus images, proposing a network with edge-aware losses and adversarial training to render realistic bokeh effects, achieving pleasing results with sharp edges in complex scenes.
In this paper, we tackle the problem of monocular bokeh synthesis, where we attempt to render a shallow depth of field image from a single all-in-focus image. Unlike in DSLR cameras, this effect can not be captured directly in mobile cameras due to the physical constraints of the mobile aperture. We thus propose a network-based approach that is capable of rendering realistic monocular bokeh from single image inputs. To do this, we introduce three new edge-aware Bokeh Losses based on a predicted monocular depth map, that sharpens the foreground edges while blurring the background. This model is then finetuned using an adversarial loss to generate a realistic Bokeh effect. Experimental results show that our approach is capable of generating a pleasing, natural Bokeh effect with sharp edges while handling complicated scenes.