# SteReFo: Efficient Image Refocusing with Stereo Vision

arXiv: https://arxiv.org/abs/1909.13395 · HTML: https://mlsanity.com/paper/1909.13395/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2019.

## Built on by (most cited first, 25 of 25)

- [BokehMe: When Neural Rendering Meets Classical Rendering](https://mlsanity.com/paper/2206.12614/) (2022)
- [Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2110.08192/) (2021)
- [DoF-NeRF: Depth-of-Field Meets Neural Radiance Fields](https://mlsanity.com/paper/2208.00945/) (2022)
- [On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks](https://mlsanity.com/paper/2303.14840/) (2023)
- [Is my Depth Ground-Truth Good Enough? HAMMER -- Highly Accurate Multi-Modal Dataset for DEnse 3D Scene Regression](https://mlsanity.com/paper/2205.04565/) (2022)
- [Stacked Deep Multi-Scale Hierarchical Network for Fast Bokeh Effect Rendering from a Single Image](https://mlsanity.com/paper/2105.07174/) (2021)
- [MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects](https://mlsanity.com/paper/2207.08403/) (2022)
- [Wild ToFu: Improving Range and Quality of Indirect Time-of-Flight Depth with RGB Fusion in Challenging Environments](https://mlsanity.com/paper/2112.03750/) (2021)
- [Bokehlicious: Photorealistic Bokeh Rendering with Controllable Apertures](https://mlsanity.com/paper/2503.16067/) (2025)
- [Defocus to focus: Photo-realistic bokeh rendering by fusing defocus and radiance priors](https://mlsanity.com/paper/2306.04506/) (2023)
- [BokehDiff: Neural Lens Blur with One-Step Diffusion](https://mlsanity.com/paper/2507.18060/) (2025)
- [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)
- [Natural & Adversarial Bokeh Rendering via Circle-of-Confusion Predictive Network](https://mlsanity.com/paper/2111.12971/) (2021)
- [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)
- [BokehFlow: Depth-Free Controllable Bokeh Rendering via Flow Matching](https://mlsanity.com/paper/2511.15066/) (2025)
- [The First Controllable Bokeh Rendering Challenge at NTIRE 2026](https://mlsanity.com/paper/2605.05510/) (2026)
- [DwinFormer: Dual Window Transformers for End-to-End Monocular Depth Estimation](https://mlsanity.com/paper/2303.02968/) (2023)
- [Semi-Supervised Semantic Depth Estimation using Symbiotic Transformer and NearFarMix Augmentation](https://mlsanity.com/paper/2308.14400/) (2023)
- [Any-to-Bokeh: Arbitrary-Subject Video Refocusing with Video Diffusion Model](https://mlsanity.com/paper/2505.21593/) (2025)
- [AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer](https://mlsanity.com/paper/2606.31959/) (2026)
- [GBSD: Generative Bokeh with Stage Diffusion](https://mlsanity.com/paper/2306.08251/) (2023)
- [Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework](https://mlsanity.com/paper/2605.07429/) (2026)

## Abstract (arXiv)

Whether to attract viewer attention to a particular object, give the impression of depth or simply reproduce human-like scene perception, shallow depth of field images are used extensively by professional and amateur photographers alike. To this end, high quality optical systems are used in DSLR cameras to focus on a specific depth plane while producing visually pleasing bokeh. We propose a physically motivated pipeline to mimic this effect from all-in-focus stereo images, typically retrieved by mobile cameras. It is capable to change the focal plane a posteriori at 76 FPS on KITTI images to enable real-time applications. As our portmanteau suggests, SteReFo interrelates stereo-based depth estimation and refocusing efficiently. In contrast to other approaches, our pipeline is simultaneously fully differentiable, physically motivated, and agnostic to scene content. It also enables computational video focus tracking for moving objects in addition to refocusing of static images. We evaluate our approach on the publicly available datasets SceneFlow, KITTI, CityScapes and quantify the quality of architectural changes.