# Natural & Adversarial Bokeh Rendering via Circle-of-Confusion Predictive Network

arXiv: https://arxiv.org/abs/2111.12971 · HTML: https://mlsanity.com/paper/2111.12971/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 58 references that are in the map.
- First posted on arXiv 25 Nov 2021.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Spatially Transformed Adversarial Examples](https://mlsanity.com/paper/1801.02612/) (2018)
- [Defocus Deblurring Using Dual-Pixel Data](https://mlsanity.com/paper/2005.00305/) (2020)
- [Adversarial Attacks and Defences Competition](https://mlsanity.com/paper/1804.00097/) (2018)
- [ColorFool: Semantic Adversarial Colorization](https://mlsanity.com/paper/1911.10891/) (2019)
- [Semantic Adversarial Examples](https://mlsanity.com/paper/1804.00499/) (2018)
- [Iterative Filter Adaptive Network for Single Image Defocus Deblurring](https://mlsanity.com/paper/2108.13610/) (2021)
- [Unrestricted Adversarial Examples via Semantic Manipulation](https://mlsanity.com/paper/1904.06347/) (2019)
- [Synthetic Depth-of-Field with a Single-Camera Mobile Phone](https://mlsanity.com/paper/1806.04171/) (2018)
- [Rendering Natural Camera Bokeh Effect with Deep Learning](https://mlsanity.com/paper/2006.05698/) (2020)
- [SPA-GAN: Spatial Attention GAN for Image-to-Image Translation](https://mlsanity.com/paper/1908.06616/) (2019)
- [Learning to Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data](https://mlsanity.com/paper/2012.03255/) (2020)
- [ADef: an Iterative Algorithm to Construct Adversarial Deformations](https://mlsanity.com/paper/1804.07729/) (2018)
- [SteReFo: Efficient Image Refocusing with Stereo Vision](https://mlsanity.com/paper/1909.13395/) (2019)
- [BGGAN: Bokeh-Glass Generative Adversarial Network for Rendering Realistic Bokeh](https://mlsanity.com/paper/2011.02242/) (2020)
- [Stacked Deep Multi-Scale Hierarchical Network for Fast Bokeh Effect Rendering from a Single Image](https://mlsanity.com/paper/2105.07174/) (2021)
- [Pasadena: Perceptually Aware and Stealthy Adversarial Denoise Attack](https://mlsanity.com/paper/2007.07097/) (2020)
- [Depth-aware Blending of Smoothed Images for Bokeh Effect Generation](https://mlsanity.com/paper/2005.14214/) (2020)
- [Classifying degraded images over various levels of degradation](https://mlsanity.com/paper/2006.08145/) (2020)
- [Nonuniform Defocus Removal for Image Classification](https://mlsanity.com/paper/2106.13864/) (2021)

## Built on by (most cited first, 4 of 4)

- [Texture Re-scalable Universal Adversarial Perturbation](https://mlsanity.com/paper/2406.06089/) (2024)
- [StructGS: Adaptive Spherical Harmonics and Rendering Enhancements for Superior 3D Gaussian Splatting](https://mlsanity.com/paper/2503.06462/) (2025)
- [Variable Aperture Bokeh Rendering via Customized Focal Plane Guidance](https://mlsanity.com/paper/2410.14400/) (2024)
- [AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant T2I Adversarial Patches](https://mlsanity.com/paper/2506.09538/) (2025)

## Abstract (arXiv)

Bokeh effect is a natural shallow depth-of-field phenomenon that blurs the out-of-focus part in photography. In recent years, a series of works have proposed automatic and realistic bokeh rendering methods for artistic and aesthetic purposes. They usually employ cutting-edge data-driven deep generative networks with complex training strategies and network architectures. However, these works neglect that the bokeh effect, as a real phenomenon, can inevitably affect the subsequent visual intelligent tasks like recognition, and their data-driven nature prevents them from studying the influence of bokeh-related physical parameters (i.e., depth-of-the-field) on the intelligent tasks. To fill this gap, we study a totally new problem, i.e., natural & adversarial bokeh rendering, which consists of two objectives: rendering realistic and natural bokeh and fooling the visual perception models (i.e., bokeh-based adversarial attack). To this end, beyond the pure data-driven solution, we propose a hybrid alternative by taking the respective advantages of data-driven and physical-aware methods. Specifically, we propose the circle-of-confusion predictive network (CoCNet) by taking the all-in-focus image and depth image as inputs to estimate circle-of-confusion parameters for each pixel, which are employed to render the final image through a well-known physical model of bokeh. With the hybrid solution, our method could achieve more realistic rendering results with the naive training strategy and a much lighter network.