AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Q-REAL: Towards Naturalness and Distortion Evaluation for AI-Generated Content

Shushi Wang, Zicheng Zhang, Chunyi Li, Wei Wang, Liya Ma, Xiaoyu Li, Fengjiao Chen, Xuezhi Cao, Guangtao Zhai, Xiaohong Liu

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Interleaved image-text generation with MLLMs · 0 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
fine-tune on Q-Real (Stages 1-2) instead of zero-shotQwen2.5-VL-7B-Instruct · ImageQA Distortiondetection rate: 0.059 -> 0.548Improved
fine-tune on Q-Real instead of zero-shotQwen3-VL-8B-Instruct · ImageQA Naturalnessdetection rate: 0.313 -> 0.548Improved
fine-tune on Q-Real instead of zero-shotQwen2.5-VL-7B-Instruct · ObjectQA Naturalness Q1accuracy: 0.605 -> 0.751Improved
fine-tune on Q-Real instead of zero-shotInternVL3-8B · ImageQA NaturalnessLLM score: 0.230 -> 0.737Improved
fine-tune on Q-Real instead of zero-shotQwen3-VL-8B-Instruct · ImageQA NaturalnessIoU: 0.848 -> 0.834No clear effect
add Stage 1 object-level judgment training before Stage 2 (ablation)Qwen2.5-VL-7B-Instruct · ImageQA DistortionLLM score: 0.623 -> 0.633Improved
add Stage 1 object-level judgment training before Stage 2 (ablation)InternVL2.5-8B · ImageQA Distortiondetection rate: 0.418 -> 0.448Improved
add Stage 1 object-level judgment training before Stage 2 (ablation)Qwen3-VL-8B-Instruct · ImageQA NaturalnessLLM score: 0.721 -> 0.722No clear effect
add training-inference consistency to Stage 3 prompt (ablation)Q-Real-Score · Q-Real Bench quality scoringSRCC: 0.692 -> 0.710Improved
add naturalness CoT issues to Stage 3 prompt (ablation)Q-Real-Score · Q-Real Bench quality scoringSRCC: 0.700 -> 0.710Improved
add distortion CoT issues to Stage 3 prompt (ablation)Q-Real-Score · Q-Real Bench quality scoringSRCC: 0.696 -> 0.710Improved
use detailed issue descriptions in prompt (Q-Real-Score) instead of Q-Eval-Score general CoTQwen3-VL-8B · AGIQA-3KSRCC: 0.587 -> 0.608Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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