MV-RAG: Retrieval Augmented Multiview Diffusion
By: Yosef Dayani, Omer Benishu, Sagie Benaim
Potential Business Impact:
Makes 3D objects from rare ideas.
Text-to-3D generation approaches have advanced significantly by leveraging pretrained 2D diffusion priors, 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. 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.
Similar Papers
VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents
Computation and Language
Helps computers understand pictures and text in documents.
Fashion-RAG: Multimodal Fashion Image Editing via Retrieval-Augmented Generation
CV and Pattern Recognition
Lets you design clothes by just describing them.
VimoRAG: Video-based Retrieval-augmented 3D Motion Generation for Motion Language Models
CV and Pattern Recognition
Makes computer characters move more realistically from videos.