DeepAI AI Chat
Log In Sign Up

FishEyeRecNet: A Multi-Context Collaborative Deep Network for Fisheye Image Rectification

by   Xiaoqing Yin, et al.

Images captured by fisheye lenses violate the pinhole camera assumption and suffer from distortions. Rectification of fisheye images is therefore a crucial preprocessing step for many computer vision applications. In this paper, we propose an end-to-end multi-context collaborative deep network for removing distortions from single fisheye images. In contrast to conventional approaches, which focus on extracting hand-crafted features from input images, our method learns high-level semantics and low-level appearance features simultaneously to estimate the distortion parameters. To facilitate training, we construct a synthesized dataset that covers various scenes and distortion parameter settings. Experiments on both synthesized and real-world datasets show that the proposed model significantly outperforms current state of the art methods. Our code and synthesized dataset will be made publicly available.


page 1

page 6

page 11

page 12

page 14


Learning Multi-level Deep Representations for Image Emotion Classification

In this paper, we propose a new deep network that learns multi-level dee...

Deep Image Harmonization

Compositing is one of the most common operations in photo editing. To ge...

Dirty Pixels: Optimizing Image Classification Architectures for Raw Sensor Data

Real-world sensors suffer from noise, blur, and other imperfections that...

Object-Level Context Modeling For Scene Classification with Context-CNN

Convolutional Neural Networks (CNNs) have been used extensively for comp...

JPAD-SE: High-Level Semantics for Joint Perception-Accuracy-Distortion Enhancement in Image Compression

While humans can effortlessly transform complex visual scenes into simpl...

End-to-end Animal Image Matting

Extracting accurate foreground animals from natural animal images benefi...

Scene Text Synthesis for Efficient and Effective Deep Network Training

A large amount of annotated training images is critical for training acc...