AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

MDMR-Bench: A Multi-Dimensional Benchmark for Multi-Reference Image Generation

Bowen Zheng, Jintao Lin, Chang-Heng Yi, HAORAN YANG, Binxiao Huang, Chenyang Lei, Rui Liu, Xihui Liu

NeurIPS 2026 · Image generation › Text-to-image diffusion · approach: Fairness and bias in generative models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces MDMR-Bench, a multi-dimensional benchmark for evaluating multi-reference image generation models conditioned on multiple reference images and text instructions.

Problem

Existing benchmarks for multi-reference image generation rely on limited evaluation dimensions and fail to capture the diverse challenges of conditioning on multiple reference images with textual instructions.

Approach

A benchmark that evaluates multi-reference image generation along multiple dimensions (e.g., entity fusion and attribute transfer across images), in place of the narrower evaluation axes of prior benchmarks.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use checklist-based instead of score-based evaluation (ablation)MDMR-Bench evaluation protocol · MDMR-Bench judgesinter-judge agreement (Krippendorff's alpha)Improved
increase number of reference images from two to four (ablation)multi-reference generation models · Attribute Transfer subsetOverall score (0-1 scale): lower by roughly 0.106 (Composition roughly 0.122)Hurt
swap real reference images for synthetic ones (ablation)Nano Banana Pro · 100 paired casesOverall (%): 87.01 -> 87.44No clear effect
swap real reference images for synthetic ones (ablation)Seedream 5.0 · 100 paired casesOverall (%): 82.93 -> 83.16No clear effect
switch judge from Gemini-3-Pro to GPT-5.4 (ablation)MDMR-Bench leaderboard · MDMR-Benchmodel rankingNo clear effect
pack multiple elements in a single reference image (multi-element extraction) versus several separate referencesmulti-reference generation models · MDMR-Bench task familiesOverall checklist scoreImproved
infographic manipulation instead of entity fusion tasksall models except Nano Banana Pro · MDMR-Bench task familiesOverall checklist scoreHurt
human-related attribute transfer (expression, makeup, outfit, pose, hair) versus other content typesmulti-reference generation models · Attribute Transfer subsetOverall checklist scoreHurt

Experimental setup

Benchmarks: MDMR-Bench

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