Vision-language models achieve at most 61.9% accuracy on identifying image distortion types and severities, falling short of human majority-vote performance at 65.7%.
The unreasonable effectiveness of deep features as a perceptual metric
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
method 2
background 1
citation-polarity summary
fields
cs.CV 8verdicts
UNVERDICTED 8representative citing papers
CASR enables stable arbitrary-scale super-resolution by breaking extreme magnifications into cyclic in-distribution transitions with SSAM for structural distribution alignment and SARM for texture self-similarity preservation.
EmoCtrl generates images faithful to content prompts while expressing target emotions via textual/visual enhancement modules and emotion-driven preference optimization.
ZeroIDIR restores illumination-degraded images via adaptive gamma correction followed by perturbed consistency diffusion, trained solely on degraded images without references.
The LoViF 2026 Challenge creates the SeIQA dataset and benchmark for human-oriented semantic image quality assessment, with six submitted solutions reaching state-of-the-art performance.
Nano Banana 2 delivers competitive perceptual quality on image restoration but produces over-enhanced results that diverge from input fidelity in ways standard metrics miss.
The LoViF 2026 challenge introduces a short-form video weather removal dataset and summarizes results from 5 valid submissions out of 37 participants.
The NTIRE 2026 challenge reports strong performance from 17 teams on raindrop removal for dual-focused day and night images using an adjusted real-world dataset with 14,139 training images.
citing papers explorer
-
DistortBench: Benchmarking Vision Language Models on Image Distortion Identification
Vision-language models achieve at most 61.9% accuracy on identifying image distortion types and severities, falling short of human majority-vote performance at 65.7%.
-
CASR: A Robust Cyclic Framework for Arbitrary Large-Scale Super-Resolution with Distribution Alignment and Self-Similarity Awareness
CASR enables stable arbitrary-scale super-resolution by breaking extreme magnifications into cyclic in-distribution transitions with SSAM for structural distribution alignment and SARM for texture self-similarity preservation.
-
EmoCtrl: Controllable Emotional Image Content Generation
EmoCtrl generates images faithful to content prompts while expressing target emotions via textual/visual enhancement modules and emotion-driven preference optimization.
-
ZeroIDIR: Zero-Reference Illumination Degradation Image Restoration with Perturbed Consistency Diffusion Models
ZeroIDIR restores illumination-degraded images via adaptive gamma correction followed by perturbed consistency diffusion, trained solely on degraded images without references.
-
LoViF 2026 Challenge on Human-oriented Semantic Image Quality Assessment: Methods and Results
The LoViF 2026 Challenge creates the SeIQA dataset and benchmark for human-oriented semantic image quality assessment, with six submitted solutions reaching state-of-the-art performance.
-
Can Nano Banana 2 Replace Traditional Image Restoration Models? An Evaluation of Its Performance on Image Restoration Tasks
Nano Banana 2 delivers competitive perceptual quality on image restoration but produces over-enhanced results that diverge from input fidelity in ways standard metrics miss.
-
LoViF 2026 The First Challenge on Weather Removal in Videos
The LoViF 2026 challenge introduces a short-form video weather removal dataset and summarizes results from 5 valid submissions out of 37 participants.
-
NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results
The NTIRE 2026 challenge reports strong performance from 17 teams on raindrop removal for dual-focused day and night images using an adjusted real-world dataset with 14,139 training images.