paper-with-me

홈 › Papers

SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuning

2024-11-15 · Zewen Chen, Juan Wang, Wen Wang, Sunhan Xu, Hang Xiong, Yun Zeng, Jian Guo, Shuxun Wang, Chunfeng Yuan, Bing Li, Weiming Hu

Existing Image Quality Assessment (IQA) methods achieve remarkable success in analyzing quality for overall image, but few works explore quality analysis for Regions of Interest (ROIs). The quality analysis of ROIs can provide fine-grained guidance for image quality improvement and is crucial for scenarios focusing on region-level quality. This paper proposes a novel network, SEAGULL, which can SEe and Assess ROIs quality with GUidance from a Large vision-Language model. SEAGULL incorporates a vision-language model (VLM), masks generated by Segment Anything Model (SAM) to specify ROIs, and a meticulously designed Mask-based Feature Extractor (MFE) to extract global and local tokens for specified ROIs, enabling accurate fine-grained IQA for ROIs. Moreover, this paper constructs two ROI-based IQA datasets, SEAGULL-100w and SEAGULL-3k, for training and evaluating ROI-based IQA. SEAGULL-100w comprises about 100w synthetic distortion images with 33 million ROIs for pre-training to improve the model's ability of regional quality perception, and SEAGULL-3k contains about 3k authentic distortion ROIs to enhance the model's ability to perceive real world distortions. After pre-training on SEAGULL-100w and fine-tuning on SEAGULL-3k, SEAGULL shows remarkable performance on fine-grained ROI quality assessment. Code and datasets are publicly available at the https://github.com/chencn2020/Seagull.

📄 PDF Abstract BibTeX arXiv:2411.10161

Code (1)

chencn2020/seagull 공식 구현 pytorch

Tasks

Image Quality AssessmentLanguage ModelingLanguage ModellingNo-Reference Image Quality Assessment

Similar Papers 제목 키워드 기반

Seagull: An Infrastructure for Load Prediction and Optimized Resource Allocation

2020-09-27 · Olga Poppe, Tayo Amuneke, Dalitso Banda, Aritra De 외

Microsoft Azure is dedicated to guarantee high quality of service to its customers, in particular, during periods of high customer activity, while controlling cost. We employ a Data Science (DS) driven solution to predic…

Scheduling

Image Quality Assessment with Gradient Siamese Network

2022-08-08 · Heng Cong, Lingzhi Fu, Rongyu Zhang, Yusheng Zhang 외

In this work, we introduce Gradient Siamese Network (GSN) for image quality assessment. The proposed method is skilled in capturing the gradient features between distorted images and reference images in full-reference im…

Full reference image quality assessmentFull-Reference Image Quality AssessmentImage Quality Assessment

PR-IQA: Partial-Reference Image Quality Assessment for Diffusion-Based Novel View Synthesis

2026-04-06 · Inseong Choi, Siwoo Lee, Seung-Hun Nam, Soohwan Song arxiv

Diffusion models are promising for sparse-view novel view synthesis (NVS), as they can generate pseudo-ground-truth views to aid 3D reconstruction pipelines like 3D Gaussian Splatting (3DGS). However, these synthesized i…

Image Quality AssessmentNovel View Synthesis3D Reconstruction

CG-DIQA: No-reference Document Image Quality Assessment Based on Character Gradient

2018-07-11 · Hongyu Li, Fan Zhu, Junhua Qiu

Document image quality assessment (DIQA) is an important and challenging problem in real applications. In order to predict the quality scores of document images, this paper proposes a novel no-reference DIQA method based…

Document Image Quality AssessmentImage Quality AssessmentOptical Character Recognition (OCR)

MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment

2022-04-19 · Sidi Yang, Tianhe Wu, Shuwei Shi, Shanshan Lao 외

No-Reference Image Quality Assessment (NR-IQA) aims to assess the perceptual quality of images in accordance with human subjective perception. Unfortunately, existing NR-IQA methods are far from meeting the needs of pred…

Image Quality AssessmentNo-Reference Image Quality Assessment