Bokeh-Loss GAN: Multi-Stage Adversarial Training for Realistic Edge-Aware Bokeh
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 27 of its 47 references that are in the map. First posted on arXiv 25 Aug 2022.
Builds on
27 of 47 references.
References · 27
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2022Generative Adversarial Networkscited by 5,627
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
- 2017Improved Training of Wasserstein GANscited by 2,235
- 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
- 2021Vision Transformers for Dense Predictioncited by 1,803
- 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
- 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
- 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
- 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
- 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
- 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
15 more
- 2022Simple Baselines for Image Restorationcited by 708
- 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 367
- 2017DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networkscited by 156
- 2019AI Benchmark: All About Deep Learning on Smartphones in 2019cited by 77
- 2018Synthetic Depth-of-Field with a Single-Camera Mobile Phonecited by 71
- 2020Rendering Natural Camera Bokeh Effect with Deep Learningcited by 57
- 2022BokehMe: When Neural Rendering Meets Classical Renderingcited by 48
- 2016Deep Shading: Convolutional Neural Networks for Screen-Space Shadingcited by 46
- 2021TRACER: Extreme Attention Guided Salient Object Tracing Networkcited by 33
- 2017Fast Deep Matting for Portrait Animation on Mobile Phonecited by 30
- 2020AIM 2020 Challenge on Rendering Realistic Bokehcited by 26
- 2019SteReFo: Efficient Image Refocusing with Stereo Visioncited by 25
- 2020BGGAN: Bokeh-Glass Generative Adversarial Network for Rendering Realistic Bokehcited by 19
- 2021Stacked Deep Multi-Scale Hierarchical Network for Fast Bokeh Effect Rendering from a Single Imagecited by 18
- 2022Joint Prediction of Monocular Depth and Structure using Planar and Parallax Geometrycited by 4
Built on by
Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 0; 2026: 1.
3 papers.