Progressively Complementary Network for Fisheye Image Rectification Using Appearance Flow

  title={Progressively Complementary Network for Fisheye Image Rectification Using Appearance Flow},
  author={Shangrong Yang and Chunyu Lin and Kang Liao and Chunjie Zhang and Yao Zhao},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  • Shangrong Yang, Chunyu Lin, +2 authors Yao Zhao
  • Published 30 March 2021
  • Computer Science
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Distortion rectification is often required for fisheye images. The generation-based method is one mainstream solution due to its label-free property, but its naive skip-connection and overburdened decoder will cause blur and incomplete correction. First, the skip-connection directly transfers the image features, which may introduce distortion and cause incomplete correction. Second, the decoder is overburdened during simultaneously reconstructing the content and structure of the image… Expand
DocScanner: Robust Document Image Rectification with Progressive Learning
  • Hao Feng, Wengang Zhou, Jiajun Deng, Qi Tian, Houqiang Li
  • Computer Science
  • ArXiv
  • 2021
This work presents DocScanner, a new deep network architecture for document image rectification, which outperforms previous methods on OCR accuracy, image similarity, and the proposed distortion metric by a considerable margin. Expand
The Multi-Modal Video Reasoning and Analyzing Competition
  • Haoran Peng, He Huang, +15 authors Tao Lin
  • Computer Science
  • 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
  • 2021
This paper summarizes the top performing methods submitted by the participants in this competition, and shows their results achieved in the competition. Expand


Learning to Calibrate Straight Lines for Fisheye Image Rectification
This paper proposes a novel deep neural network to impose explicit geometry constraints onto processes of the fisheye lens calibration and the distorted image rectification, and achieves the best published rectification quality and the most accurate estimation of distortion parameters on a large set of synthetic and real f isheye images. Expand
Model-Free Distortion Rectification Framework Bridged by Distortion Distribution Map
This work proposes a model-free distortion rectification framework for the single-shot case, bridged by the distortion distribution map (DDM), and develops a dual-stream feature learning module, benefitting from both the advantages of traditional methods that leverage the local handcrafted feature and learning-based methods that focus on the global semantic feature perception. Expand
FishEyeRecNet: A Multi-Context Collaborative Deep Network for Fisheye Image Rectification
This paper proposes an end-to-end multi-context collaborative deep network for removing distortions from single fisheye images and shows that the proposed model significantly outperforms current state of the art methods. Expand
Line-based Multi-Label Energy Optimization for fisheye image rectification and calibration
This paper proposes an easily implemented fisheye image rectification algorithm with line constrains in the undistorted perspective image plane that outperforms the existing approaches and the commercial software in most cases. Expand
DR-GAN: Automatic Radial Distortion Rectification Using Conditional GAN in Real-Time
The DR-GAN trained using the proposed low-to-high perceptual loss learns the mapping relation between different structural images rather than estimating multifarious distortion parameters, while also realizing label-free training and one-stage rectification. Expand
DeepCalib: a deep learning approach for automatic intrinsic calibration of wide field-of-view cameras
This work builds upon the recent developments in deep Convolutional Neural Networks (CNN) and automatically estimates the intrinsic parameters of the camera from a single input image, using the great amount of omnidirectional images available on the Internet to generate a large-scale dataset. Expand
Radial Lens Distortion Correction Using Convolutional Neural Networks Trained with Synthesized Images
Inspired by the growing availability of image dataset with non-radial distortion, this paper proposes a framework to address the issue by synthesizing images with radial distortion for CNNs and presents quantitative results that demonstrate the ability of the technique to estimate the radial distortion with comparisons against several baseline methods. Expand
Blind Geometric Distortion Correction on Images Through Deep Learning
This work proposes the first general framework to automatically correct different types of geometric distortion in a single input image, using convolutional neural networks trained by using a large synthetic distortion dataset to predict the displacement field. Expand
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
  • C. Ledig, Lucas Theis, +6 authors W. Shi
  • Computer Science, Mathematics
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
SRGAN, a generative adversarial network (GAN) for image super-resolution (SR), is presented, to its knowledge, the first framework capable of inferring photo-realistic natural images for 4x upscaling factors and a perceptual loss function which consists of an adversarial loss and a content loss. Expand
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
This work considers image transformation problems, and proposes the use of perceptual loss functions for training feed-forward networks for image transformation tasks, and shows results on image style transfer, where aFeed-forward network is trained to solve the optimization problem proposed by Gatys et al. in real-time. Expand