LL-Bench supplies a human-annotated dataset exposing generative model weaknesses in low-level restoration and introduces LL-Score as an MLLM evaluator that outperforms existing quality metrics and can serve as a training reward.
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Blau_The_ Perception-Distortion_Tradeoff_CVPR_2018_paper.html
7 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
verdicts
UNVERDICTED 7roles
background 2polarities
background 2representative citing papers
Neural reconstruction losses in VAEs reduce latent information content and produce more isotropic latent geometries with even uncertainty distribution.
MSIQ is a scale-invariant, model-free quality metric for single image super-resolution using normalized central geometric moments for direct comparison of different-resolution images.
HazeMatching adapts conditional flow matching with hazy-image guidance to dehaze microscopy images while balancing fidelity and realism on synthetic and real data.
Flow matching achieves single-step pixel accuracy and 20-step perceptual quality for Sentinel-2 super-resolution, outperforming diffusion and Real-ESRGAN while enabling large-scale 2.5 m land-cover products.
Training-inference input alignment outweighs framework choice for longitudinal retinal image prediction, with deterministic regression matching complex models when acquisition variability dominates disease progression.
Lightweight U-Net outperforms DDPM on T2w-to-MRI-SFF translation (r=0.975 vs 0.962, MAE=0.014 vs 0.019) with 208x faster inference on 230k paired images from NAKO.
citing papers explorer
-
LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models
LL-Bench supplies a human-annotated dataset exposing generative model weaknesses in low-level restoration and introduces LL-Score as an MLLM evaluator that outperforms existing quality metrics and can serve as a training reward.
-
How Neural Losses Shape VAE Latents
Neural reconstruction losses in VAEs reduce latent information content and produce more isotropic latent geometries with even uncertainty distribution.
-
MSIQ: Moment-based Scale-Invariant Quality Measure for Single Image Super-Resolution
MSIQ is a scale-invariant, model-free quality metric for single image super-resolution using normalized central geometric moments for direct comparison of different-resolution images.
-
HazeMatching: Dehazing Light Microscopy Images with Guided Conditional Flow Matching
HazeMatching adapts conditional flow matching with hazy-image guidance to dehaze microscopy images while balancing fidelity and realism on synthetic and real data.
-
Flow matching for Sentinel-2 super-resolution: implementation, application, and implications
Flow matching achieves single-step pixel accuracy and 20-step perceptual quality for Sentinel-2 super-resolution, outperforming diffusion and Real-ESRGAN while enabling large-scale 2.5 m land-cover products.
-
Training-inference input alignment outweighs framework choice in longitudinal retinal image prediction
Training-inference input alignment outweighs framework choice for longitudinal retinal image prediction, with deterministic regression matching complex models when acquisition variability dominates disease progression.
-
Do We Really Need Diffusion? A Fast U-Net for Paired Medical Image Translation
Lightweight U-Net outperforms DDPM on T2w-to-MRI-SFF translation (r=0.975 vs 0.962, MAE=0.014 vs 0.019) with 208x faster inference on 230k paired images from NAKO.