# BokehMe: When Neural Rendering Meets Classical Rendering

arXiv: https://arxiv.org/abs/2206.12614 · HTML: https://mlsanity.com/paper/2206.12614/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 40 references that are in the map.
- First posted on arXiv 25 Jun 2022.

## Builds on (most cited first, 13 of 13)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Deep Image Matting](https://mlsanity.com/paper/1703.03872/) (2017)
- [Indices Matter: Learning to Index for Deep Image Matting](https://mlsanity.com/paper/1908.00672/) (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)
- [Deep Shading: Convolutional Neural Networks for Screen-Space Shading](https://mlsanity.com/paper/1603.06078/) (2016)
- [Synthetic Defocus and Look-Ahead Autofocus for Casual Videography](https://mlsanity.com/paper/1905.06326/) (2019)
- [AIM 2020 Challenge on Rendering Realistic Bokeh](https://mlsanity.com/paper/2011.04988/) (2020)
- [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)

## Built on by (most cited first, 30 of 48)

- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [Less is More: Consistent Video Depth Estimation with Masked Frames Modeling](https://mlsanity.com/paper/2208.00380/) (2022)
- [DoF-NeRF: Depth-of-Field Meets Neural Radiance Fields](https://mlsanity.com/paper/2208.00945/) (2022)
- [Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis](https://mlsanity.com/paper/2412.02168/) (2024)
- [AKiRa: Augmentation Kit on Rays for optical video generation](https://mlsanity.com/paper/2412.14158/) (2024)
- [DC2: Dual-Camera Defocus Control by Learning to Refocus](https://mlsanity.com/paper/2304.03285/) (2023)
- [Bokehlicious: Photorealistic Bokeh Rendering with Controllable Apertures](https://mlsanity.com/paper/2503.16067/) (2025)
- [Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2503.08434/) (2025)
- [BokehDiff: Neural Lens Blur with One-Step Diffusion](https://mlsanity.com/paper/2507.18060/) (2025)
- [NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation](https://mlsanity.com/paper/2307.08695/) (2023)
- [Efficient Unified Demosaicing for Bayer and Non-Bayer Patterned Image Sensors](https://mlsanity.com/paper/2307.10667/) (2023)
- [Dynamic Neural Radiance Field From Defocused Monocular Video](https://mlsanity.com/paper/2407.05586/) (2024)
- [DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splatting](https://mlsanity.com/paper/2503.00746/) (2025)
- [DiffCamera: Arbitrary Refocusing on Images](https://mlsanity.com/paper/2509.26599/) (2025)
- [Point-and-Shoot All-in-Focus Photo Synthesis from Smartphone Camera Pair](https://mlsanity.com/paper/2304.04917/) (2023)
- [Scale-Invariant Monocular Depth Estimation via SSI Depth](https://mlsanity.com/paper/2406.09374/) (2024)
- [Self-Distilled Depth Refinement with Noisy Poisson Fusion](https://mlsanity.com/paper/2409.17880/) (2024)
- [Generative Refocusing: Flexible Defocus Control from a Single Image](https://mlsanity.com/paper/2512.16923/) (2025)
- [Bokeh-Loss GAN: Multi-Stage Adversarial Training for Realistic Edge-Aware Bokeh](https://mlsanity.com/paper/2208.12343/) (2022)
- [Adaptive Mask-based Pyramid Network for Realistic Bokeh Rendering](https://mlsanity.com/paper/2210.16078/) (2022)
- [BokehOrNot: Transforming Bokeh Effect with Image Transformer and Lens Metadata Embedding](https://mlsanity.com/paper/2306.04032/) (2023)
- [HG3-NeRF: Hierarchical Geometric, Semantic, and Photometric Guided Neural Radiance Fields for Sparse View Inputs](https://mlsanity.com/paper/2401.11711/) (2024)
- [FADE: A Task-Agnostic Upsampling Operator for Encoder-Decoder Architectures](https://mlsanity.com/paper/2407.13500/) (2024)
- [Generative Photographic Control for Scene-Consistent Video Cinematic Editing](https://mlsanity.com/paper/2511.12921/) (2025)
- [BokehFlow: Depth-Free Controllable Bokeh Rendering via Flow Matching](https://mlsanity.com/paper/2511.15066/) (2025)
- [Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Report](https://mlsanity.com/paper/2211.06769/) (2022)
- [The First Controllable Bokeh Rendering Challenge at NTIRE 2026](https://mlsanity.com/paper/2605.05510/) (2026)
- [Variable Aperture Bokeh Rendering via Customized Focal Plane Guidance](https://mlsanity.com/paper/2410.14400/) (2024)
- [Any-to-Bokeh: Arbitrary-Subject Video Refocusing with Video Diffusion Model](https://mlsanity.com/paper/2505.21593/) (2025)
- [Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos](https://mlsanity.com/paper/2510.10691/) (2025)

## Abstract (arXiv)

We propose BokehMe, a hybrid bokeh rendering framework that marries a neural renderer with a classical physically motivated renderer. Given a single image and a potentially imperfect disparity map, BokehMe generates high-resolution photo-realistic bokeh effects with adjustable blur size, focal plane, and aperture shape. To this end, we analyze the errors from the classical scattering-based method and derive a formulation to calculate an error map. Based on this formulation, we implement the classical renderer by a scattering-based method and propose a two-stage neural renderer to fix the erroneous areas from the classical renderer. The neural renderer employs a dynamic multi-scale scheme to efficiently handle arbitrary blur sizes, and it is trained to handle imperfect disparity input. Experiments show that our method compares favorably against previous methods on both synthetic image data and real image data with predicted disparity. A user study is further conducted to validate the advantage of our method.