mlsanityData to 7 Oct 2026

Perspective Fields for Single Image Camera Calibration

arXiv 2212.03239 ↗First posted 6 Dec 2022cs.CVcited by 75

Not on the map. Why?

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.

Key facts. Cited by 75 papers in the map (data through 7 Oct 2026). Builds on 20 of its 55 references that are in the map. First posted on arXiv 6 Dec 2022.

Builds on

20 of 55 references.

References · 20

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2022A ConvNet for the 2020scited by 3,545
  4. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  5. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  6. 2018Albumentations: fast and flexible image augmentationscited by 558
  7. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 494
  8. 2019PointRend: Image Segmentation as Renderingcited by 439
  9. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
  10. 2020Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotationscited by 155
  11. 2017A Perceptual Measure for Deep Single Image Camera Calibrationcited by 45
  12. 2018Context-Aware Synthesis and Placement of Object Instancescited by 41
8 more
  1. 2021CTRL-C: Camera calibration TRansformer with Line-Classificationcited by 33
  2. 2016Horizon Lines in the Wildcited by 30
  3. 2019Blind Geometric Distortion Correction on Images Through Deep Learningcited by 28
  4. 2016Detecting Vanishing Points using Global Image Context in a Non-Manhattan Worldcited by 27
  5. 2017Quantitative Analysis of Automatic Image Cropping Algorithms: A Dataset and Comparative Studycited by 26
  6. 2019UprightNet: Geometry-Aware Camera Orientation Estimation from Single Imagescited by 26
  7. 2020Single View Metrology in the Wildcited by 20
  8. 2020Neural Geometric Parser for Single Image Camera Calibrationcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 22; 2025: 22; 2026: 23.

75 papers.

Sort:

By area:

  1. 2024SpatialRGPT: Grounded Spatial Reasoning in Vision Language Modelscited by 297
  2. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 290
  3. 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 198
  4. 2024WonderWorld: Interactive 3D Scene Generation from a Single Imagecited by 197
  5. 2025WorldScore: A Unified Evaluation Benchmark for World Generationcited by 143
  6. 2024CameraHMR: Aligning People with Perspectivecited by 64
  7. 2023Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for nowcited by 61
  8. 2024Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single Viewcited by 59
  9. 2024SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priorscited by 53
  10. 2024GeoCalib: Learning Single-image Calibration with Geometric Optimizationcited by 50
  11. 2024Cubify Anything: Scaling Indoor 3D Object Detectioncited by 39
  12. 2023FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flowcited by 38
38 more
  1. 2025Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Cameracited by 38
  2. 2025SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Modelscited by 37
  3. 2023Tame a Wild Camera: In-the-Wild Monocular Camera Calibrationcited by 34
  4. 2025From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulationcited by 34
  5. 2023Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Modelcited by 29
  6. 2023PSDR-Room: Single Photo to Scene using Differentiable Renderingcited by 23
  7. 2023Deep Learning for Camera Calibration and Beyond: A Surveycited by 20
  8. 2025Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generationcited by 19
  9. 2023Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotationcited by 18
  10. 2024VersaT2I: Improving Text-to-Image Models with Versatile Rewardcited by 17
  11. 2025AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibrationcited by 17
  12. 2024ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusioncited by 16
  13. 2025PreciseCam: Precise Camera Control for Text-to-Image Generationcited by 13
  14. 2025Dual-Process Image Generationcited by 12
  15. 2026WildDet3D: Scaling Promptable 3D Detection in the Wildcited by 12
  16. 2025SceneMI: Motion In-betweening for Modeling Human-Scene Interactionscited by 11
  17. 2026MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sourcescited by 10
  18. 2024DiffCalib: Reformulating Monocular Camera Calibration as Diffusion-Based Dense Incident Map Generationcited by 9
  19. 2024SDFit: 3D Object Pose and Shape by Fitting a Morphable SDF to a Single Imagecited by 9
  20. 2025GenSpace: Benchmarking Spatially-Aware Image Generationcited by 9
  21. 2025Towards Scalable Spatial Intelligence via 2D-to-3D Data Liftingcited by 8
  22. 2024Detecting Origin Attribution for Text-to-Image Diffusion Modelscited by 7
  23. 2024Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibrationcited by 7
  24. 2026360Anything: Geometry-Free Lifting of Images and Videos to 360degcited by 7
  25. 2024Extreme Rotation Estimation in the Wildcited by 6
  26. 2025Spatiotemporally Consistent Indoor Lighting Estimation with Diffusion Priorscited by 5
  27. 2023Mitigating Perspective Distortion-induced Shape Ambiguity in Image Cropscited by 4
  28. 2025Bridging Vision Language Models and Symbolic Grounding for Video Question Answeringcited by 4
  29. 2024Floating No More: Object-Ground Reconstruction from a Single Imagecited by 3
  30. 2026PixARMesh: Autoregressive Mesh-Native Single-View Scene Reconstructioncited by 3
  31. 2024M"obius Transform for Mitigating Perspective Distortions in Representation Learningcited by 2
  32. 2024PaintScene4D: Consistent 4D Scene Generation from Text Promptscited by 2
  33. 2025AlignDiff: Learning Physically-Grounded Camera Alignment via Diffusioncited by 2
  34. 2025InFlux: A Benchmark for Self-Calibration of Dynamic Intrinsics of Video Camerascited by 2
  35. 2025GimbalDiffusion: Gravity-Aware Camera Control for Video Generationcited by 2
  36. 2026CalibAnyView: Beyond Single-View Camera Calibration in the Wildcited by 2
  37. 2026G3T Up! Gravity Aligned Coordinate Frames Simplify Pointmap Processingcited by 2
  38. 2024fCOP: Focal Length Estimation from Category-level Object Priorscited by 1

50 most cited of 75 All 75 (JSON)