# Perspective Fields for Single Image Camera Calibration

arXiv: https://arxiv.org/abs/2212.03239 · HTML: https://mlsanity.com/paper/2212.03239/

## Key facts

- Cited by 75 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 55 references that are in the map.
- First posted on arXiv 6 Dec 2022.

## Builds on (most cited first, 20 of 20)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [PointRend: Image Segmentation as Rendering](https://mlsanity.com/paper/1912.08193/) (2019)
- [Joint 2D-3D-Semantic Data for Indoor Scene Understanding](https://mlsanity.com/paper/1702.01105/) (2017)
- [Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations](https://mlsanity.com/paper/2012.09988/) (2020)
- [A Perceptual Measure for Deep Single Image Camera Calibration](https://mlsanity.com/paper/1712.01259/) (2017)
- [Context-Aware Synthesis and Placement of Object Instances](https://mlsanity.com/paper/1812.02350/) (2018)
- [CTRL-C: Camera calibration TRansformer with Line-Classification](https://mlsanity.com/paper/2109.02259/) (2021)
- [Horizon Lines in the Wild](https://mlsanity.com/paper/1604.02129/) (2016)
- [Blind Geometric Distortion Correction on Images Through Deep Learning](https://mlsanity.com/paper/1909.03459/) (2019)
- [Detecting Vanishing Points using Global Image Context in a Non-Manhattan World](https://mlsanity.com/paper/1608.05684/) (2016)
- [Quantitative Analysis of Automatic Image Cropping Algorithms: A Dataset and Comparative Study](https://mlsanity.com/paper/1701.01480/) (2017)
- [UprightNet: Geometry-Aware Camera Orientation Estimation from Single Images](https://mlsanity.com/paper/1908.07070/) (2019)
- [Single View Metrology in the Wild](https://mlsanity.com/paper/2007.09529/) (2020)
- [Neural Geometric Parser for Single Image Camera Calibration](https://mlsanity.com/paper/2007.11855/) (2020)

## Built on by (most cited first, 30 of 75)

- [SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models](https://mlsanity.com/paper/2406.01584/) (2024)
- [MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision](https://mlsanity.com/paper/2410.19115/) (2024)
- [MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors](https://mlsanity.com/paper/2412.12392/) (2024)
- [WonderWorld: Interactive 3D Scene Generation from a Single Image](https://mlsanity.com/paper/2406.09394/) (2024)
- [WorldScore: A Unified Evaluation Benchmark for World Generation](https://mlsanity.com/paper/2504.00983/) (2025)
- [CameraHMR: Aligning People with Perspective](https://mlsanity.com/paper/2411.08128/) (2024)
- [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)
- [Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View](https://mlsanity.com/paper/2404.03421/) (2024)
- [SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors](https://mlsanity.com/paper/2403.13438/) (2024)
- [GeoCalib: Learning Single-image Calibration with Geometric Optimization](https://mlsanity.com/paper/2409.06704/) (2024)
- [Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera](https://mlsanity.com/paper/2501.02464/) (2025)
- [FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow](https://mlsanity.com/paper/2306.00180/) (2023)
- [Cubify Anything: Scaling Indoor 3D Object Detection](https://mlsanity.com/paper/2412.04458/) (2024)
- [SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models](https://mlsanity.com/paper/2505.00788/) (2025)
- [From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation](https://mlsanity.com/paper/2505.08548/) (2025)
- [Tame a Wild Camera: In-the-Wild Monocular Camera Calibration](https://mlsanity.com/paper/2306.10988/) (2023)
- [Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Model](https://mlsanity.com/paper/2312.13252/) (2023)
- [PSDR-Room: Single Photo to Scene using Differentiable Rendering](https://mlsanity.com/paper/2307.03244/) (2023)
- [Deep Learning for Camera Calibration and Beyond: A Survey](https://mlsanity.com/paper/2303.10559/) (2023)
- [Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation](https://mlsanity.com/paper/2510.08673/) (2025)
- [Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation](https://mlsanity.com/paper/2303.11329/) (2023)
- [AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration](https://mlsanity.com/paper/2503.12701/) (2025)
- [VersaT2I: Improving Text-to-Image Models with Versatile Reward](https://mlsanity.com/paper/2403.18493/) (2024)
- [ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusion](https://mlsanity.com/paper/2410.08168/) (2024)
- [WildDet3D: Scaling Promptable 3D Detection in the Wild](https://mlsanity.com/paper/2604.08626/) (2026)
- [PreciseCam: Precise Camera Control for Text-to-Image Generation](https://mlsanity.com/paper/2501.12910/) (2025)
- [Dual-Process Image Generation](https://mlsanity.com/paper/2506.01955/) (2025)
- [SceneMI: Motion In-betweening for Modeling Human-Scene Interactions](https://mlsanity.com/paper/2503.16289/) (2025)
- [MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources](https://mlsanity.com/paper/2601.22054/) (2026)
- [DiffCalib: Reformulating Monocular Camera Calibration as Diffusion-Based Dense Incident Map Generation](https://mlsanity.com/paper/2405.15619/) (2024)

## Abstract (arXiv)

Geometric camera calibration is often required for applications that understand the perspective of the image. We propose perspective fields as a representation that models the local perspective properties of an image. Perspective Fields contain per-pixel information about the camera view, parameterized as an up vector and a latitude value. This representation has a number of advantages as it makes minimal assumptions about the camera model and is invariant or equivariant to common image editing operations like cropping, warping, and rotation. It is also more interpretable and aligned with human perception. We train a neural network to predict Perspective Fields and the predicted Perspective Fields can be converted to calibration parameters easily. We demonstrate the robustness of our approach under various scenarios compared with camera calibration-based methods and show example applications in image compositing.