{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Daily Paper Cast","title":"MV-RAG: Retrieval Augmented Multiview Diffusion","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/17d02cc6\"></iframe>","width":"100%","height":180,"duration":1232,"description":"\n            🤗 Upvotes: 31 | cs.CV, cs.AI\n\n            Authors:\n            Yosef Dayani, Omer Benishu, Sagie Benaim\n\n            Title:\n            MV-RAG: Retrieval Augmented Multiview Diffusion\n\n            Arxiv:\n            http://arxiv.org/abs/2508.16577v1\n\n            Abstract:\n            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.\n            ","thumbnail_url":"https://img.transistorcdn.com/8lOVNnuwhrA3rxrDMv7Osu4j_t1-jORooO6NfGcQhcw/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS81Zjg1/YzRhODczMDU4MmE4/OGMwN2FiNDlmYzI2/MDliMi5qcGVn.webp","thumbnail_width":300,"thumbnail_height":300}