# The Camera Inside the Editor: Reading the Implicit Camera of Image Editors with Painted Calibration Patterns

arXiv: https://arxiv.org/abs/2609.37732 · HTML: https://mlsanity.com/paper/2609.37732/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 47 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 30 of 30)

- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details](https://mlsanity.com/paper/2507.02546/) (2025)
- [OmniGen2: Towards Instruction-Aligned Multimodal Generation](https://mlsanity.com/paper/2506.18871/) (2025)
- [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026)
- [Probing the 3D Awareness of Visual Foundation Models](https://mlsanity.com/paper/2404.08636/) (2024)
- [Zoom To Learn, Learn To Zoom](https://mlsanity.com/paper/1905.05169/) (2019)
- [Perspective Fields for Single Image Camera Calibration](https://mlsanity.com/paper/2212.03239/) (2022)
- [DiffusionLight: Light Probes for Free by Painting a Chrome Ball](https://mlsanity.com/paper/2312.09168/) (2023)
- [Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now](https://mlsanity.com/paper/2311.17138/) (2023)
- [GeoCalib: Learning Single-image Calibration with Geometric Optimization](https://mlsanity.com/paper/2409.06704/) (2024)
- [Generative Models: What Do They Know? Do They Know Things? Let's Find Out!](https://mlsanity.com/paper/2311.17137/) (2023)
- [Image Generators are Generalist Vision Learners](https://mlsanity.com/paper/2604.20329/) (2026)
- [Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model](https://mlsanity.com/paper/2306.05720/) (2023)
- [Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis](https://mlsanity.com/paper/2412.02168/) (2024)
- [Single View Metrology in the Wild](https://mlsanity.com/paper/2007.09529/) (2020)
- [Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation](https://mlsanity.com/paper/2510.08673/) (2025)
- [AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration](https://mlsanity.com/paper/2503.12701/) (2025)
- [Enhancing Diffusion Models with 3D Perspective Geometry Constraints](https://mlsanity.com/paper/2312.00944/) (2023)
- [SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing](https://mlsanity.com/paper/2604.04911/) (2026)
- [DiffCalib: Reformulating Monocular Camera Calibration as Diffusion-Based Dense Incident Map Generation](https://mlsanity.com/paper/2405.15619/) (2024)
- [Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration](https://mlsanity.com/paper/2411.17240/) (2024)
- [GCC: Generative Color Constancy via Diffusing a Color Checker](https://mlsanity.com/paper/2502.17435/) (2025)
- [Open-Source Image Editing Models Are Zero-Shot Vision Learners](https://mlsanity.com/paper/2605.04566/) (2026)
- [Camera Control for Text-to-Image Generation via Learning Viewpoint Tokens](https://mlsanity.com/paper/2604.19954/) (2026)
- [ControlVP: Interactive Geometric Refinement of AI-Generated Images with Consistent Vanishing Points](https://mlsanity.com/paper/2512.07504/) (2025)
- [GenScale: A Benchmark for Relative Object Scale in Image Generation and Editing](https://mlsanity.com/paper/2609.00525/) (2026)
- [CameraEditor: Camera-Controlled Image Editing via Video-Prior Sequential Modeling](https://mlsanity.com/paper/2609.01479/) (2026)
- [Are Image Generators Zero-Shot Perceivers? A Rigorous Evaluation](https://mlsanity.com/paper/2609.07884/) (2026)
- [Shedding Light: A Benchmark for Evaluating Lighting Understanding in Generative Image Models](https://mlsanity.com/paper/2609.10787/) (2026)

## Built on by (most cited first, 1 of 1)

- [Do Image Editors Follow Depth-Dependent Blur and Aperture Response? A Rendered-Ground-Truth Pilot Audit](https://mlsanity.com/paper/2610.09344/) (2026)

## Abstract (arXiv)

Instruction-based image editors insert objects, restyle scenes and render new viewpoints, but it is unknown which camera they assume when they paint into a photograph. Asked to cover the floor with a checkerboard, an editor paints projective structure from which classical vanishing-point geometry reads pitch, roll, focal length, yaw and, on renders, the principal point, without any training. Unlike a calibrator such as GeoCalib, which estimates the camera of an image, this isolates the camera under which the editor paints. On 120 rendered cameras with exact ground truth, Qwen-Image-Edit-2511 paints tile edges that meet their vanishing points within 0.26 degrees, and its implicit camera matches the true one to 0.8 degrees in pitch and 6% in focal length, more accurately than GeoCalib except in roll. Asked to draw the horizon or mark a vanishing point instead, the editor fails, so this knowledge is revealed by painting and not by the explicit tasks we tried. The implicit camera has two priors: roll is pulled towards level (slope 0.71), and telephoto perspective towards a default of about 30 mm, which roughly matches the camera the models paint without any scene. For Qwen, the priors do not grow when blur removes four fifths of the line evidence. They are stronger on real photographs, and on NYUv2 a shorter wording of the task removes the difference for roll. On photographs from a 24--240 mm zoom lens the painted perspective grows with only 0.62 of the lens's slope, while GeoCalib and MoGe-2 saturate at about 52 and 42 mm. FLUX.1 Kontext and LongCat-Image-Edit are pulled much harder. Finally, from a level camera a camera-control LoRA executes pose commands at only 50--70% of their strength, and a board painted into its output agrees with the camera it produced.