Tagged articles
image quality assessment
12 articles · Page 1 of 1
iDetex, the champion solution of the ICCV 2025 MIPI Detailed Image Quality Assessment Challenge, introduces a novel multimodal LLM-driven framework that precisely locates, describes, and grades image distortions, outperforming traditional IQA models and enabling practical deployments across video, live streaming, e‑commerce, and image‑processing pipelines.
AIComputer VisionICCV 2025
0 likes · 18 min read


AIWalkerAug 3, 2025 · Artificial Intelligence
DeQA-Score introduces a soft‑label discretization that lets multimodal large language models regress continuous image‑quality scores as Gaussian distributions, achieving 30× lower mean error and preserving variance and inter‑image relationships, with KL‑divergence and fidelity losses driving state‑of‑the‑art performance.
CVPR2025DeQA-Scoreimage quality assessment
0 likes · 8 min read


AIWalkerJun 30, 2025 · Artificial Intelligence
The ICCV MIPI workshop introduces the ViDA-UGC competition, presenting a richly annotated UGC image quality dataset, a benchmark suite covering degradation detection, region perception, and quality description, detailed evaluation metrics, submission formats, prize information, and open participation for researchers worldwide.
DatasetICCVMIPI
0 likes · 15 min read


AIWalkerApr 11, 2025 · Artificial Intelligence
DeQA-Score, a CVPR 2025 work, shows how to train multimodal large language models to regress continuous image quality scores by discretizing scores into soft-label level tokens, preserving Gaussian distribution statistics and achieving state‑of‑the‑art performance without any installation.
CVPR2025DeQA-Scoreimage quality assessment
0 likes · 8 min read

Q-Insight, a multimodal large‑model introduced by Peking University and Volcano Engine, leverages reinforcement learning and a novel Group Relative Policy Optimization algorithm to evaluate image quality, providing detailed reasoning, degradation detection, and zero‑shot comparison, outperforming state‑of‑the‑art methods on multiple benchmarks.
AIComputer VisionMultimodal Model
0 likes · 10 min read


AIWalkerFeb 9, 2025 · Artificial Intelligence
At CVPR 2024 NTIRE, Douyin’s BDVQAGroup achieved second place worldwide in the DXOMARK portrait quality track using their SampleIQA model, which combines data‑re‑sampling, a Swin‑Transformer backbone, twin‑network ranking loss and content‑aware cropping to outperform existing IQA state‑of‑the‑art methods.
Computer VisionDXOMARKNTIRE2024
0 likes · 10 min read


AIWalkerFeb 8, 2025 · Artificial Intelligence
The CVPR 2025 NTIRE workshop launches an AI-generated image quality assessment competition featuring two tracks—fine‑grained text‑image matching and structural issue detection—supported by the large‑scale EvalMuse dataset, detailed evaluation metrics, baseline code, and a prize pool of up to $10,000.
AI competitionCVPREvalMuse
0 likes · 9 min read

The article reviews recent automated quality assessment advances for AIGC image generation, including an aesthetic scoring framework with the APDD dataset and AANSPS network, a human‑preference benchmark (HPD v2 and HPS v2) that outperforms IS/FID, and the Pick‑Score model trained on user‑driven Pick‑a‑Pic data, all enabling faster, unbiased evaluation, cost savings, and more effective model iteration, with ongoing work in home‑improvement AI.
AIGCHuman Preferenceaesthetic evaluation
0 likes · 15 min read


ITPUBJul 21, 2022 · Artificial Intelligence
This article reviews image quality assessment fundamentals, modern CNN‑based IQA models, and their deployment at 58.com to automatically score, filter, and rank millions of recruitment photos, achieving a drop in low‑quality images from 9% to zero while boosting overall accuracy to 94.7%.
Business ApplicationCNNComputer Vision
0 likes · 19 min read


58 TechJul 14, 2022 · Artificial Intelligence
This article reviews image quality assessment (IQA) methods—including full‑reference, reduced‑reference, and no‑reference approaches—covers typical datasets and evaluation metrics, describes CNN‑based models such as WaDIQaM, DBCNN and hyperIQA, and details a customized IQA solution deployed at 58.com to filter and rank recruitment images, achieving a reduction of bad‑image rate from 9% to 0%.
CNNComputer VisionIQA
0 likes · 17 min read

The paper presents RISA, a reference‑guided image synthesis assessment model that learns to score the quality of a single generated image without human‑labeled data by leveraging GAN intermediate outputs, pixel‑wise interpolation, multiple binary classifiers, and contrastive learning, achieving results comparable to human perception and earning an AAAI 2022 oral presentation.
AIGANRISA
0 likes · 8 min read

The article describes an intelligent cover‑image selection system for NetEase News that automatically filters unsuitable illustrations, assesses image quality with a pairwise‑trained deep model across clarity, color and composition, and smartly crops images using aspect‑ratio‑aware object detection, dramatically cutting manual editing and enabling confidence‑based automatic publishing.
Computer VisionImage CroppingNeural Network
0 likes · 11 min read
