SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.01338 · 2020

Comparison of Image Quality Models for Optimization of Image Processing Systems

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
dingkeyan93/IQA-optimization canonical 2 of 2
FunctionStatusWhere it lives
gaussian_filter Ran dingkeyan93/IQA-optimization/IQA_pytorch/SSIM.py
code served (permissive licence) · get_code("e62294c5d41ce581")
ssim Ran dingkeyan93/IQA-optimization/IQA_pytorch/SSIM.py
code served (permissive licence) · get_code("87bcff3e68316051")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The performance of objective image quality assessment (IQA) models has been evaluated primarily by comparing model predictions to human quality judgments. Perceptual datasets gathered for this purpose have provided useful benchmarks for improving IQA methods, but their heavy use creates a risk of overfitting. Here, we perform a large-scale comparison of IQA models in terms of their use as objectives for the optimization of image processing algorithms. Specifically, we use eleven full-reference IQA models to train deep neural networks for four low-level vision tasks: denoising, deblurring, super-resolution, and compression. Subjective testing on the optimized images allows us to rank the competing models in terms of their perceptual performance, elucidate their relative advantages and disadvantages in these tasks, and propose a set of desirable properties for incorporation into future IQA models.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2005.01338")
get_code_for_paper("2005.01338")
have("2005.01338")

Connect an agent — have() is free.