Salvato in:
Dettagli Bibliografici
Autori principali: Oshima, Yuta, Miyake, Daiki, Matsutani, Kohsei, Iwasawa, Yusuke, Suzuki, Masahiro, Matsuo, Yutaka, Furuta, Hiroki
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2511.22989
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915891419021312
author Oshima, Yuta
Miyake, Daiki
Matsutani, Kohsei
Iwasawa, Yusuke
Suzuki, Masahiro
Matsuo, Yutaka
Furuta, Hiroki
author_facet Oshima, Yuta
Miyake, Daiki
Matsutani, Kohsei
Iwasawa, Yusuke
Suzuki, Masahiro
Matsuo, Yutaka
Furuta, Hiroki
contents Recent text-to-image generation models have acquired the ability of multi-reference generation and editing; that is, to inherit the appearance of subjects from multiple reference images and re-render them in new contexts. However, existing benchmark datasets often focus on generation using a single or a few reference images, which prevents us from measuring progress in model performance or identifying weaknesses when following instructions with a larger number of references. In addition, their task definitions are still vague, limited to axes such as ``what to edit'' or ``how many references are given'', and therefore fail to capture the challenges inherent in combining heterogeneous references. To address this gap, we introduce MultiBanana, which is designed to assess the edge of model capabilities by widely covering problems specific to multi-reference settings: (1) varying the number of references (up to 8), (2) domain mismatch among references (e.g., photo vs. anime), (3) scale mismatch between reference and target scenes, (4) references containing rare concepts (e.g., a red banana), and (5) multilingual textual references for rendering. Our analysis among a variety of text-to-image models reveals their respective performances, typical failure modes, and areas for improvement. MultiBanana is released as an open benchmark to push the boundaries and establish a standardized basis for fair comparison in multi-reference image generation. Our data and code are available at https://github.com/matsuolab/multibanana .
format Preprint
id arxiv_https___arxiv_org_abs_2511_22989
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation
Oshima, Yuta
Miyake, Daiki
Matsutani, Kohsei
Iwasawa, Yusuke
Suzuki, Masahiro
Matsuo, Yutaka
Furuta, Hiroki
Computer Vision and Pattern Recognition
Recent text-to-image generation models have acquired the ability of multi-reference generation and editing; that is, to inherit the appearance of subjects from multiple reference images and re-render them in new contexts. However, existing benchmark datasets often focus on generation using a single or a few reference images, which prevents us from measuring progress in model performance or identifying weaknesses when following instructions with a larger number of references. In addition, their task definitions are still vague, limited to axes such as ``what to edit'' or ``how many references are given'', and therefore fail to capture the challenges inherent in combining heterogeneous references. To address this gap, we introduce MultiBanana, which is designed to assess the edge of model capabilities by widely covering problems specific to multi-reference settings: (1) varying the number of references (up to 8), (2) domain mismatch among references (e.g., photo vs. anime), (3) scale mismatch between reference and target scenes, (4) references containing rare concepts (e.g., a red banana), and (5) multilingual textual references for rendering. Our analysis among a variety of text-to-image models reveals their respective performances, typical failure modes, and areas for improvement. MultiBanana is released as an open benchmark to push the boundaries and establish a standardized basis for fair comparison in multi-reference image generation. Our data and code are available at https://github.com/matsuolab/multibanana .
title MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.22989