mlsanityData to 7 Oct 2026

Blind Geometric Distortion Correction on Images Through Deep Learning

arXiv 1909.03459 ↗First posted 8 Sep 2019cs.CVcited by 28

Not on the map. Why?

Abstract (arXiv)

We propose the first general framework to automatically correct different types of geometric distortion in a single input image. Our proposed method employs convolutional neural networks (CNNs) trained by using a large synthetic distortion dataset to predict the displacement field between distorted images and corrected images. A model fitting method uses the CNN output to estimate the distortion parameters, achieving a more accurate prediction. The final corrected image is generated based on the predicted flow using an efficient, high-quality resampling method. Experimental results demonstrate that our algorithm outperforms traditional correction methods, and allows for interesting applications such as distortion transfer, distortion exaggeration, and co-occurring distortion correction.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 5; 2023: 7; 2024: 5; 2025: 8; 2026: 1.

28 papers.

Sort:

By area:

  1. 2022Perspective Fields for Single Image Camera Calibrationcited by 75
  2. 2021Progressively Complementary Network for Fisheye Image Rectification Using Appearance Flowcited by 23
  3. 2023Deep Learning for Camera Calibration and Beyond: A Surveycited by 20
  4. 2022SeamlessGAN: Self-Supervised Synthesis of Tileable Texture Mapscited by 19
  5. 2025Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generationcited by 19
  6. 2025AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibrationcited by 17
  7. 2023SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learningcited by 13
  8. 2022FishFormer: Annulus Slicing-based Transformer for Fisheye Rectification with Efficacy Domain Explorationcited by 8
  9. 2023RecRecNet: Rectangling Rectified Wide-Angle Images by Thin-Plate Spline Model and DoF-based Curriculum Learningcited by 8
  10. 2021Rethinking Generic Camera Models for Deep Single Image Camera Calibration to Recover Rotation and Fisheye Distortioncited by 6
  11. 2022Water Simulation and Rendering from a Still Photographcited by 5
  12. 2023Dual Diffusion Architecture for Fisheye Image Rectification: Synthetic-to-Real Generalizationcited by 5
16 more
  1. 2022FisheyeEX: Polar Outpainting for Extending the FoV of Fisheye Lenscited by 2
  2. 2023Spatiotemporal Deformation Perception for Fisheye Video Rectificationcited by 2
  3. 2023Camera Calibration without Camera Access -- A Robust Validation Technique for Extended PnP Methodscited by 2
  4. 2024M"obius Transform for Mitigating Perspective Distortions in Representation Learningcited by 2
  5. 2025AlignDiff: Learning Physically-Grounded Camera Alignment via Diffusioncited by 2
  6. 2025Accelerating Vehicle Routing via AI-Initialized Genetic Algorithmscited by 2
  7. 2024QueryCDR: Query-Based Controllable Distortion Rectification Network for Fisheye Imagescited by 1
  8. 2025Robustness of Structured Data Extraction from Perspectively Distorted Documentscited by 1
  9. 2023Visual Question Answering (VQA) on Images with Superimposed Textcited by 0
  10. 2024RoFIR: Robust Fisheye Image Rectification Framework Impervious to Optical Center Deviationcited by 0
  11. 2024LCM: Log Conformal Maps for Robust Representation Learning to Mitigate Perspective Distortioncited by 0
  12. 2024Predicting the Reliability of an Image Classifier under Image Distortioncited by 0
  13. 2025A Deep Single Image Rectification Approach for Pan-Tilt-Zoom Camerascited by 0
  14. 2025DCA-LUT: Deep Chromatic Alignment with 5D LUT for Purple Fringing Removalcited by 0
  15. 2025Rectification Reimagined: A Unified Mamba Model for Image Correction and Rectangling with Promptscited by 0
  16. 2026Puffin-World: Scaling a Unified Multimodal Model with Native 3D World Statescited by 0