The SIU²A framework evaluates scientific images for error detection, repair feasibility, and correction quality, showing current multimodal systems have major limitations in preserving scientific validity.
Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment
2 Pith papers cite this work, alongside 1,085 external citations. Polarity classification is still indexing.
2
Pith papers citing it
1,085
external citations · external index
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
baseline 1polarities
baseline 1representative citing papers
MSDS computes DeepSSIM at multiple pyramid scales and fuses the scores with learned weights, producing consistent improvements over single-scale DeepSSIM on IQA benchmarks with negligible extra cost.
citing papers explorer
-
Towards Characterizing Scientific Image Utility and Upgradability
The SIU²A framework evaluates scientific images for error detection, repair feasibility, and correction quality, showing current multimodal systems have major limitations in preserving scientific validity.
-
MSDS: Deep Structural Similarity with Multiscale Representation
MSDS computes DeepSSIM at multiple pyramid scales and fuses the scores with learned weights, producing consistent improvements over single-scale DeepSSIM on IQA benchmarks with negligible extra cost.