# DiffCamera: Arbitrary Refocusing on Images

arXiv: https://arxiv.org/abs/2509.26599 · HTML: https://mlsanity.com/paper/2509.26599/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 43 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Synthetic Depth-of-Field with a Single-Camera Mobile Phone](https://mlsanity.com/paper/1806.04171/) (2018)
- [MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation](https://mlsanity.com/paper/2502.04299/) (2025)
- [BokehMe: When Neural Rendering Meets Classical Rendering](https://mlsanity.com/paper/2206.12614/) (2022)
- [Synthetic Defocus and Look-Ahead Autofocus for Casual Videography](https://mlsanity.com/paper/1905.06326/) (2019)
- [SteReFo: Efficient Image Refocusing with Stereo Vision](https://mlsanity.com/paper/1909.13395/) (2019)
- [Stacked Deep Multi-Scale Hierarchical Network for Fast Bokeh Effect Rendering from a Single Image](https://mlsanity.com/paper/2105.07174/) (2021)
- [DeepLens: Shallow Depth Of Field From A Single Image](https://mlsanity.com/paper/1810.08100/) (2018)
- [Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2503.08434/) (2025)

## Built on by (most cited first, 5 of 5)

- [Generative Refocusing: Flexible Defocus Control from a Single Image](https://mlsanity.com/paper/2512.16923/) (2025)
- [Fine-grained Defocus Blur Control for Generative Image Models](https://mlsanity.com/paper/2510.06215/) (2025)
- [Boosting Monocular Metric Depth Estimation via Bokeh Rendering](https://mlsanity.com/paper/2512.12425/) (2025)
- [AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer](https://mlsanity.com/paper/2606.31959/) (2026)
- [LensStyle: Learning the Optical Aesthetics for Controllable Stylized Lens Effect Rendering](https://mlsanity.com/paper/2609.04939/) (2026)

## Abstract (arXiv)

The depth-of-field (DoF) effect, which introduces aesthetically pleasing blur, enhances photographic quality but is fixed and difficult to modify once the image has been created. This becomes problematic when the applied blur is undesirable~(e.g., the subject is out of focus). To address this, we propose DiffCamera, a model that enables flexible refocusing of a created image conditioned on an arbitrary new focus point and a blur level. Specifically, we design a diffusion transformer framework for refocusing learning. However, the training requires pairs of data with different focus planes and bokeh levels in the same scene, which are hard to acquire. To overcome this limitation, we develop a simulation-based pipeline to generate large-scale image pairs with varying focus planes and bokeh levels. With the simulated data, we find that training with only a vanilla diffusion objective often leads to incorrect DoF behaviors due to the complexity of the task. This requires a stronger constraint during training. Inspired by the photographic principle that photos of different focus planes can be linearly blended into a multi-focus image, we propose a stacking constraint during training to enforce precise DoF manipulation. This constraint enhances model training by imposing physically grounded refocusing behavior that the focusing results should be faithfully aligned with the scene structure and the camera conditions so that they can be combined into the correct multi-focus image. We also construct a benchmark to evaluate the effectiveness of our refocusing model. Extensive experiments demonstrate that DiffCamera supports stable refocusing across a wide range of scenes, providing unprecedented control over DoF adjustments for photography and generative AI applications.