Towards improved lossy image compression: Human image reconstruction with public-domain images

10/25/2018
by   Ashutosh Bhown, et al.
0

Lossy image compression has been studied extensively in the context of typical loss functions such as RMSE, MS-SSIM, etc. However, compression at low bitrates generally produces unsatisfying results. Furthermore, the availability of massive public image datasets appears to have hardly been exploited in image compression. Here, we present a paradigm for eliciting human image reconstruction in order to perform lossy image compression. In this paradigm, one human describes images to a second human, whose task is to reconstruct the target image using publicly available images and text instructions. The resulting reconstructions are then evaluated by human raters on the Amazon Mechanical Turk platform and compared to reconstructions obtained using state-of-the-art compressor WebP. Our results suggest that prioritizing semantic visual elements may be key to achieving significant improvements in image compression, and that our paradigm can be used to develop a more human-centric loss function. The images, results and additional data are available at https://compression.stanford.edu/human-compression

READ FULL TEXT
research
10/25/2018

Humans are still the best lossy image compressors

Lossy image compression has been studied extensively in the context of t...
research
10/08/2019

Lossy Image Compression with Recurrent Neural Networks: from Human Perceived Visual Quality to Classification Accuracy

Deep neural networks have recently advanced the state-of-the-art in imag...
research
05/04/2023

Catch Missing Details: Image Reconstruction with Frequency Augmented Variational Autoencoder

The popular VQ-VAE models reconstruct images through learning a discrete...
research
04/07/2013

Image Compression predicated on Recurrent Iterated Function Systems

Recurrent iterated function systems (RIFSs) are improvements of iterated...
research
05/22/2019

Multiple reconstruction compression framework based on PNG image

It is shown that neural networks (NNs) achieve excellent performances in...
research
02/22/2022

Computing Multiple Image Reconstructions with a Single Hypernetwork

Deep learning based techniques achieve state-of-the-art results in a wid...
research
04/04/2022

Unsupervised Change Detection Based on Image Reconstruction Loss

To train the change detector, bi-temporal images taken at different time...

Please sign up or login with your details

Forgot password? Click here to reset