MV-RAG: Retrieval Augmented Multiview Diffusion

Yosef Dayani, Omer Benishu, Sagie Benaim

Keywords: Retrieval Augmented Generation, Multi-view Diffusion, Text-to-3D Generation

TL;DR: We propose a multiview diffuison model, that, when conditioned on 2D retrieved views matching the input text, results in state-of-the-art results, particularly on OOD or rare concepts.

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 prediction objective: the model predicts the held-out view from the 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 a rigorous 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.

Primary Area: generative models

Submission Number: 12259