@inproceedings{ishikawa-etal-2026-3d,
title = "3{D} Visual Prompting: Empowering 3{D}-Aware Visual Generation via In-Context Self-Refinement",
author = "Ishikawa, Reina and
Sato, Fumiaki and
Hachiuma, Ryo and
Sekii, Taiki and
Saito, Hideo",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2197/",
doi = "10.18653/2026.findings-emnlp.2197",
pages = "47055--47075",
ISBN = "979-8-89176-462-0",
abstract = "Recent advances in image and video generation have highlighted the need for intuitive, high-precision manipulation. However, traditional text-based prompts or 2D Visual Prompts (e.g., dragging, 2D trajectories) often suffer from unintuitive prompt engineering or depth ambiguity. To address these limitations, we introduce 3D Visual Prompting, a novel paradigm that significantly improves input intuitiveness for visual manipulation tasks. We develop a framework that integrates intuitive 3D constraints into 2D generative processes. Our approach projects 3D Visual Prompts onto 2D visual planes and leverages Multimodal Large Language Models (MLLMs) to verbalize intent, allowing plug-and-play use of existing 2D models. Furthermore, we incorporate In-Context Self-Refinement (ICSR) to summarize insights from self-correction into a meta-strategy. This enables high-precision 3D control in single-pass inference, eliminating the need for iterative computation. Experimental results demonstrate that our method significantly outperforms traditional 2D Visual Prompting for object translation and rotation. By utilizing pre-trained models without additional parameter tuning, our framework remains highly adaptable to future developments in generative models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ishikawa-etal-2026-3d">
<titleInfo>
<title>3D Visual Prompting: Empowering 3D-Aware Visual Generation via In-Context Self-Refinement</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reina</namePart>
<namePart type="family">Ishikawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fumiaki</namePart>
<namePart type="family">Sato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryo</namePart>
<namePart type="family">Hachiuma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taiki</namePart>
<namePart type="family">Sekii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideo</namePart>
<namePart type="family">Saito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Recent advances in image and video generation have highlighted the need for intuitive, high-precision manipulation. However, traditional text-based prompts or 2D Visual Prompts (e.g., dragging, 2D trajectories) often suffer from unintuitive prompt engineering or depth ambiguity. To address these limitations, we introduce 3D Visual Prompting, a novel paradigm that significantly improves input intuitiveness for visual manipulation tasks. We develop a framework that integrates intuitive 3D constraints into 2D generative processes. Our approach projects 3D Visual Prompts onto 2D visual planes and leverages Multimodal Large Language Models (MLLMs) to verbalize intent, allowing plug-and-play use of existing 2D models. Furthermore, we incorporate In-Context Self-Refinement (ICSR) to summarize insights from self-correction into a meta-strategy. This enables high-precision 3D control in single-pass inference, eliminating the need for iterative computation. Experimental results demonstrate that our method significantly outperforms traditional 2D Visual Prompting for object translation and rotation. By utilizing pre-trained models without additional parameter tuning, our framework remains highly adaptable to future developments in generative models.</abstract>
<identifier type="citekey">ishikawa-etal-2026-3d</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.2197</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2197/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>47055</start>
<end>47075</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 3D Visual Prompting: Empowering 3D-Aware Visual Generation via In-Context Self-Refinement
%A Ishikawa, Reina
%A Sato, Fumiaki
%A Hachiuma, Ryo
%A Sekii, Taiki
%A Saito, Hideo
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F ishikawa-etal-2026-3d
%X Recent advances in image and video generation have highlighted the need for intuitive, high-precision manipulation. However, traditional text-based prompts or 2D Visual Prompts (e.g., dragging, 2D trajectories) often suffer from unintuitive prompt engineering or depth ambiguity. To address these limitations, we introduce 3D Visual Prompting, a novel paradigm that significantly improves input intuitiveness for visual manipulation tasks. We develop a framework that integrates intuitive 3D constraints into 2D generative processes. Our approach projects 3D Visual Prompts onto 2D visual planes and leverages Multimodal Large Language Models (MLLMs) to verbalize intent, allowing plug-and-play use of existing 2D models. Furthermore, we incorporate In-Context Self-Refinement (ICSR) to summarize insights from self-correction into a meta-strategy. This enables high-precision 3D control in single-pass inference, eliminating the need for iterative computation. Experimental results demonstrate that our method significantly outperforms traditional 2D Visual Prompting for object translation and rotation. By utilizing pre-trained models without additional parameter tuning, our framework remains highly adaptable to future developments in generative models.
%R 10.18653/2026.findings-emnlp.2197
%U https://aclanthology.org/2026.findings-emnlp.2197/
%U https://doi.org/10.18653/2026.findings-emnlp.2197
%P 47055-47075
Markdown (Informal)
[3D Visual Prompting: Empowering 3D-Aware Visual Generation via In-Context Self-Refinement](https://aclanthology.org/2026.findings-emnlp.2197/) (Ishikawa et al., Findings 2026)
ACL