Inpainting and Denoising Challenges

The problem of dealing with missing or incomplete data in machine learning and computer vision arises in many applications. Recent strategies make use of generative models to impute missing or corrupted data. Advances in computer vision using deep generative models have found applications in image/v...

Full description

Corporate Author: SpringerLink (Online service)
Other Authors: Escalera, Sergio. (Editor, http://id.loc.gov/vocabulary/relators/edt), Ayache, Stephane. (Editor, http://id.loc.gov/vocabulary/relators/edt), Wan, Jun. (Editor, http://id.loc.gov/vocabulary/relators/edt), Madadi, Meysam. (Editor, http://id.loc.gov/vocabulary/relators/edt), Güçlü, Umut. (Editor, http://id.loc.gov/vocabulary/relators/edt), Baró, Xavier. (Editor, http://id.loc.gov/vocabulary/relators/edt)
Language:English
Published: Cham : Springer International Publishing : Imprint: Springer, 2019.
Edition:1st ed. 2019.
Series:The Springer Series on Challenges in Machine Learning,
Subjects:
Online Access:https://doi.org/10.1007/978-3-030-25614-2
Table of Contents:
  • 1. A Brief Review of Image Denoising Algorithms and Beyond
  • 2. ChaLearn Looking at People: Inpainting and Denoising Challenges
  • 3. U-Finger: Multi-Scale Dilated Convolutional Network for Fingerprint Image Denoising and Inpainting
  • 4. FPD-M-net: Fingerprint Image Denoising and Inpainting Using M-Net Based Convolutional Neural Networks
  • 5. Iterative Application of Autoencoders for Video Inpainting and Fingerprint Denoising
  • 6. Video DeCaptioning using U-Net with Stacked Dilated Convolutional Layers
  • 7. Joint Caption Detection and Inpainting using Generative Network
  • 8. Generative Image Inpainting for Person Pose Generation
  • 9. Person Inpainting with Generative Adversarial Networks
  • 10. Road Layout Understanding by Generative Adversarial Inpainting
  • 11. Photo-realistic and Robust Inpainting of Faces using Refinement GANs.