A Debye CZT-based wave-optics pipeline generates lens-diverse synthetic defocus blur datasets that improve cross-device deblurring generalization over existing real and synthetic data.
Topiq: A top-down approach from semantics to distortions for image quality assessment
5 Pith papers cite this work, alongside 199 external citations. Polarity classification is still indexing.
5
Pith papers citing it
199
external citations · external index
fields
cs.CV 5representative citing papers
Presents SPPE benchmark and ERMA/C2E-S2SER methods for editability assessment and surrogate-to-source recovery in MLLM privacy protection, reporting metric improvements.
The paper releases SR-Ground, a crowdsourced dataset for pixel-level segmentation of six artifact types in super-resolved images, and shows its use for training grounded IQA models and artifact-reducing fine-tuning.
TIQA introduces datasets and a model that predict human perceptual quality of rendered text in AI images, achieving PLCC 0.942 on crops and improving selected image text quality by 0.36 MOS.
THEval proposes eight metrics for evaluating talking head videos on quality, naturalness, and synchronization, tested on 85,000 videos from 17 models with a new curated dataset.
citing papers explorer
-
Realistic Compound-Lens Defocus Blur Synthesis
A Debye CZT-based wave-optics pipeline generates lens-diverse synthetic defocus blur datasets that improve cross-device deblurring generalization over existing real and synthetic data.
-
When Recovery Matters: The Blind Spot of Surrogate Privacy in MLLM Editing
Presents SPPE benchmark and ERMA/C2E-S2SER methods for editability assessment and surrogate-to-source recovery in MLLM privacy protection, reporting metric improvements.
-
SR-Ground: Image Quality Grounding for Super-Resolved Content
The paper releases SR-Ground, a crowdsourced dataset for pixel-level segmentation of six artifact types in super-resolved images, and shows its use for training grounded IQA models and artifact-reducing fine-tuning.
-
TIQA: Human-Aligned Perceptual Text Quality Assessment in Generated Images
TIQA introduces datasets and a model that predict human perceptual quality of rendered text in AI images, achieving PLCC 0.942 on crops and improving selected image text quality by 0.36 MOS.
-
THEval. Evaluation Framework for Talking Head Video Generation
THEval proposes eight metrics for evaluating talking head videos on quality, naturalness, and synchronization, tested on 85,000 videos from 17 models with a new curated dataset.