Vectra: A New Metric, Dataset, and Model for Visual Quality Assessment in E-Commerce In-Image Machine Translation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wu, Qingyu, Han, Yuxuan, Li, Haijun, Xu, Zhao, Zhao, Jianshan, Jin, Xu, Wang, Longyue, Luo, Weihua
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912885395947520
author Wu, Qingyu
Han, Yuxuan
Li, Haijun
Xu, Zhao
Zhao, Jianshan
Jin, Xu
Wang, Longyue
Luo, Weihua
author_facet Wu, Qingyu
Han, Yuxuan
Li, Haijun
Xu, Zhao
Zhao, Jianshan
Jin, Xu
Wang, Longyue
Luo, Weihua
contents In-Image Machine Translation (IIMT) powers cross-border e-commerce product listings; existing research focuses on machine translation evaluation, while visual rendering quality is critical for user engagement. When facing context-dense product imagery and multimodal defects, current reference-based methods (e.g., SSIM, FID) lack explainability, while model-as-judge approaches lack domain-grounded, fine-grained reward signals. To bridge this gap, we introduce Vectra, to the best of our knowledge, the first reference-free, MLLM-driven visual quality assessment framework for e-commerce IIMT. Vectra comprises three components: (1) Vectra Score, a multidimensional quality metric system that decomposes visual quality into 14 interpretable dimensions, with spatially-aware Defect Area Ratio (DAR) quantification to reduce annotation ambiguity; (2) Vectra Dataset, constructed from 1.1M real-world product images via diversity-aware sampling, comprising a 2K benchmark for system evaluation, 30K reasoning-based annotations for instruction tuning, and 3.5K expert-labeled preferences for alignment and evaluation; and (3) Vectra Model, a 4B-parameter MLLM that generates both quantitative scores and diagnostic reasoning. Experiments demonstrate that Vectra achieves state-of-the-art correlation with human rankings, and our model outperforms leading MLLMs, including GPT-5 and Gemini-3, in scoring performance. The dataset and model will be released upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2602_07014
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Vectra: A New Metric, Dataset, and Model for Visual Quality Assessment in E-Commerce In-Image Machine Translation
Wu, Qingyu
Han, Yuxuan
Li, Haijun
Xu, Zhao
Zhao, Jianshan
Jin, Xu
Wang, Longyue
Luo, Weihua
Computer Vision and Pattern Recognition
Artificial Intelligence
I.2.1; I.2.10
In-Image Machine Translation (IIMT) powers cross-border e-commerce product listings; existing research focuses on machine translation evaluation, while visual rendering quality is critical for user engagement. When facing context-dense product imagery and multimodal defects, current reference-based methods (e.g., SSIM, FID) lack explainability, while model-as-judge approaches lack domain-grounded, fine-grained reward signals. To bridge this gap, we introduce Vectra, to the best of our knowledge, the first reference-free, MLLM-driven visual quality assessment framework for e-commerce IIMT. Vectra comprises three components: (1) Vectra Score, a multidimensional quality metric system that decomposes visual quality into 14 interpretable dimensions, with spatially-aware Defect Area Ratio (DAR) quantification to reduce annotation ambiguity; (2) Vectra Dataset, constructed from 1.1M real-world product images via diversity-aware sampling, comprising a 2K benchmark for system evaluation, 30K reasoning-based annotations for instruction tuning, and 3.5K expert-labeled preferences for alignment and evaluation; and (3) Vectra Model, a 4B-parameter MLLM that generates both quantitative scores and diagnostic reasoning. Experiments demonstrate that Vectra achieves state-of-the-art correlation with human rankings, and our model outperforms leading MLLMs, including GPT-5 and Gemini-3, in scoring performance. The dataset and model will be released upon acceptance.
title Vectra: A New Metric, Dataset, and Model for Visual Quality Assessment in E-Commerce In-Image Machine Translation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
I.2.1; I.2.10
url https://arxiv.org/abs/2602.07014