AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

HRScene: How Far Are VLMs from Effective High-Resolution Image Understanding?

Yusen Zhang, Wenliang Zheng, Aashrith Madasu, Peng Shi, Ryo Kamoi, Hao Zhou, Zhuoyang Zou, Shu Zhao, Sarkar Snigdha Sarathi Das, Vipul Gupta, Xiaoxin Lu, Nan Zhang and 5 more

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add index text under each sub-image (ablation)ComplexGrid construction (Qwen2-VL 7B) · ComplexGrid 10x10accuracy: 1.53 -> 8.22Improved
add index text under each sub-image (ablation)ComplexGrid construction (InternVL2 8B) · ComplexGrid 10x10accuracy: 2.78 -> 17.15Improved
add white interval between sub-images (ablation)ComplexGrid construction (Qwen2-VL 72B) · ComplexGrid 10x10accuracy: 3.17 -> 5.17Improved
add both index and interval to dense grid (ablation)ComplexGrid construction (InternVL2 8B) · ComplexGrid 10x10accuracy: 2.78 -> 20.54Improved
add both index and interval to dense grid (ablation)ComplexGrid construction (Qwen2-VL 72B) · ComplexGrid 10x10accuracy: 3.17 -> 18.72Improved
scale model size within a familyVLMs · HRScene real-worldaccuracyImproved
increase whitebackground grid from 1x1 to 10x10DeepSeek-VL2-27B · WhiteBackground NIAHperformance: 72.06 -> 23.95Hurt
increase whitebackground grid from 1x1 to 10x10Qwen2-VL - 72B · WhiteBackground NIAHperformance: 84.13 -> 84.56No clear effect
use native-resolution input (Qwen) instead of size-limited input (GPT-4o)Qwen 72B vs GPT 4o · Galaxy (20k resolution)accuracy: 68.68 -> 80.80Improved
native-resolution input on 1k imagesQwen 72B vs GPT 4o · HRVQA (1k resolution)accuracy: 73.82 -> 69.59Hurt
resize image before input (ablation)Qwen2-VL 7B · Autonomous Driving and HR-BenchaccuracyMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy