Towards Open-ended Visual Quality Comparison
원문 초록
Comparative settings (e.g. pairwise choice, listwise ranking) have been adopted by a wide range of subjective studies for image quality assessment (IQA), as it inherently standardizes the evaluation criteria across different observers and offer more clear-cut responses. In this work, we extend the edge of emerging large multi-modality models (LMMs) to further advance visual quality comparison into open-ended settings, that 1) can respond to open-range questions on quality comparison; 2) can provide detailed reasonings beyond direct answers. To this end, we propose the Co-Instruct. To train this first-of-its-kind open-source open-ended visual quality comparer, we collect the Co-Instruct-562K dataset, from two sources: (a) LLM-merged single image quality description, (b) GPT-4V "teacher" responses on unlabeled data. Furthermore, to better evaluate this setting, we propose the MICBench, the first benchmark on multi-image comparison for LMMs. We demonstrate that Co-Instruct not only achieves in average 30% higher accuracy than state-of-the-art open-source LMMs, but also outperforms GPT-4V (its teacher), on both existing related benchmarks and the proposed MICBench. Our model is published at https://huggingface.co/q-future/co-instruct.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Text-Visual Semantic Constrained AI-Generated Image Quality Assessment
MS-IQA: A Multi-Scale Feature Fusion Network for PET/CT Image Quality Assessment
3DGS-IEval-15K: A Large-scale Image Quality Evaluation Database for 3D Gaussian-Splatting
DGIQA: Depth-guided Feature Attention and Refinement for Generalizable Image Quality Assessment
Taylor expansion-based Kolmogorov-Arnold network for blind image quality assessment
MMP-2K: A Benchmark Multi-Labeled Macro Photography Image Quality Assessment Database
토론
이 논문과 연결된 포럼 글이 아직 없습니다.