Learning to Inpaint for Image Compression

Mohammad Haris Baig, Vladlen Koltun, Lorenzo Torresani

Nov-20-2025, 21:36:06 GMT–Neural Information Processing Systems

We study the design of deep architectures for lossy image compression. We present two architectural recipes in the context of multi-stage progressive encoders and empirically demonstrate their importance on compression performance.

artificial intelligence, deep learning, machine learning, (15 more...)

Neural Information Processing Systems

Nov-20-2025, 21:36:06 GMT

Conferences PDF

Add feedback

Country:
- North America > United States
  - New Hampshire > Grafton County
    - Hanover (0.04)
  - California
    - Santa Clara County > Santa Clara (0.04)
    - Los Angeles County > Long Beach (0.04)
- Europe > Germany
  - Berlin (0.04)
- Asia > Japan
  - Honshū > Chūbu > Toyama Prefecture > Toyama (0.04)

Technology:
- Information Technology
  - Sensing and Signal Processing > Image Processing (1.00)
  - Artificial Intelligence > Machine Learning
    - Neural Networks > Deep Learning (0.89)

Duplicate Docs Excel Report

Title
Learning to Inpaint for Image Compression
Learning to Inpaint for Image Compression

Similar Docs Excel Report more

Title	Similarity	Source
None found