Skip to main navigation Skip to search Skip to main content

MV-RAG: Retrieval Augmented Multiview Diffusion

Research output: Contribution to journal › Article › peer-review

Abstract

Text-to-3D generation approaches have advanced significantly, producing high-quality and 3D-consistent outputs. However, they often fail to produce out-of-domain (OOD) or rare concepts, yielding inconsistent or inaccurate results. To this end, we propose MV-RAG, a novel text-to-3D pipeline that first retrieves relevant 2D images from a large in-the-wild 2D database and then conditions a multiview diffusion model on these images to synthesize consistent and accurate multiview outputs. Training such a retrieval-conditioned model is achieved via a novel hybrid strategy bridging structured multiview data and diverse 2D image collections. This involves training on multiview data using augmented conditioning views that simulate retrieval variance for view-specific reconstruction, alongside training on sets of retrieved real-world 2D images using a distinctive held-out view objective: the model predicts the held-out view from other views to infer 3D consistency from 2D data. We also introduce a prior-guided fusion mechanism that dynamically balances retrieval signals with the model’s prior. To facilitate OOD evaluation, we introduce a new collection of challenging OOD prompts. Experiments against state-of-the-art text-to-3D, image-to-3D, and personalization baselines show that our approach significantly improves 3D consistency, photorealism, and text adherence for OOD/rare concepts, while maintaining competitive performance on standard benchmarks. Project page: https://yosefdayani.github.io/MV-RAG/.

Original languageEnglish
JournalTransactions on Machine Learning Research
Volume2026-September
StatePublished - 2026

Bibliographical note

Publisher Copyright:
© 2026, Transactions on Machine Learning Research. All rights reserved.

Fingerprint

Dive into the research topics of 'MV-RAG: Retrieval Augmented Multiview Diffusion'. Together they form a unique fingerprint.

Cite this