paper-with-me

홈 › Papers

CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences

2026-05-30 · Fangzhou Lin, Peiran Li, Lingyu Xu, Wenjing Chen, Qianwen Ge, Shuo Xing, Mingyang Wu, Xiangbo Gao, Siyuan Yang, Kazunori Yamada, Ziming Zhang, Haichong Zhang, Zhen Dong, Ming-Hsuan Yang, Zhengzhong Tu arxiv

Instruction-guided image editing is becoming a general interface for visual work, yet existing benchmarks still focus largely on narrow appearance edits and do not fully capture the diversity of real-image tasks in professional workflows. Here, we define instructional computer vision problem solving as a broader formulation of image editing: given a real input image and a natural-language instruction, a system must produce an edited output that realizes the requested transformation while satisfying explicit preservation, geometric, physical, and usability constraints. We introduce CV-Arena, an open benchmark designed to evaluate this capability at professional scales. CV-Arena contains 12K high-resolution real-image instruction pairs spanning 16 instruction-based visual task types, constructed using CogRetriever, a dual-track retrieval-and-curation pipeline that combines targeted web search, agentic query refinement, verification, and traceability. To evaluate models at scale while preserving human fidelity, we propose Active Elo, a human-AI collaborative preference protocol that leverages CV-Judge, a logic-gated, multi-dimensional VLM evaluator, to reject clear failures and resolve high-confidence comparisons; and to route close, high-quality comparisons to expert raters. Mixed human and AI supervision is then aggregated through reliability-weighted Elo updates. Our comprehensive evaluation of 21 systems, including proprietary, open-source, and agentic models, on CV-Arena reveals persistent gaps in instruction adherence, physical reasoning, structural control, and fine-grained detail preservation. We further develop CV-Agent, a lightweight agentic model that combines planning, editing, and verification, and demonstrate that closed-loop reasoning is a promising direction for professional-grade instruction-following visual editing.

📄 PDF Abstract BibTeX arXiv:2606.00931

Code (0)

등록된 구현이 없습니다.

Tasks

Image Editing

Similar Papers 제목 키워드 기반

VisionArena: 230K Real World User-VLM Conversations with Preference Labels

2024-12-11 · CVPR 2025 1 · Christopher Chou, Lisa Dunlap, Koki Mashita, Krishna Mandal 외

With the growing adoption and capabilities of vision-language models (VLMs) comes the need for benchmarks that capture authentic user-VLM interactions. In response, we create VisionArena, a dataset of 230K real-world con…

ChatbotSpatial Reasoning

ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

2025-09-18 · Zhaoyang Liu, Jingjing Xie, Zichen Ding, Zehao Li 외 arxiv

Vision-Language Models (VLMs) have enabled computer use agents (CUAs) that operate GUIs autonomously, showing great potential, yet progress is limited by the lack of large-scale, open-source computer use data and foundat…

CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era

2025-03-16 · Kanzhi Cheng, Wenpo Song, Jiaxin Fan, Zheng Ma 외

Image captioning has been a longstanding challenge in vision-language research. With the rise of LLMs, modern Vision-Language Models (VLMs) generate detailed and comprehensive image descriptions. However, benchmarking th…

BenchmarkingImage Captioning

GameArena: Evaluating LLM Reasoning through Live Computer Games

2024-12-09 · Lanxiang Hu, Qiyu Li, Anze Xie, Nan Jiang 외

Evaluating the reasoning abilities of large language models (LLMs) is challenging. Existing benchmarks often depend on static datasets, which are vulnerable to data contamination and may get saturated over time, or on bi…

Chatbot

GeoArena: Evaluating Open-World Geographic Reasoning in Large Vision-Language Models

2025-09-04 · Pengyue Jia, Yingyi Zhang, Xiangyu Zhao, Sharon Li arxiv

Geographic reasoning is a fundamental cognitive capability that requires models to infer plausible locations by synthesizing visual evidence with spatial world knowledge. Despite recent advances in large vision-language …