Bokeh-Loss GAN: Multi-Stage Adversarial Training for Realistic Edge-Aware Bokeh

TL;DR

This paper presents a novel neural network approach for monocular bokeh synthesis from single images, using edge-aware loss functions and adversarial training to produce realistic shallow depth of field effects.

Contribution

It introduces three new edge-aware Bokeh Losses based on monocular depth prediction and combines them with adversarial training for improved bokeh rendering.

Findings

Produces natural and sharp-edged bokeh effects in complex scenes

Outperforms existing methods in realism and edge preservation

Effective in mobile camera scenarios where physical aperture control is limited

Abstract

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.