MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion

• DOI: 10.48550/arxiv.2307.01097
• Publication Date: 2023-01-01
• Authors: Tang, Shitao; Zhang, Fuyang; Chen, Jiacheng; Wang, Peng; Furukawa, Yasutaka
• Keywords: FOS: Computer and information sciences; Computer Vision and Pattern Recognition (cs.CV); Computer Science - Computer Vision and Pattern Recognition

This paper introduces MVDiffusion, a simple yet effective method for generating consistent multi-view images from text prompts given pixel-to-pixel correspondences (e.g., perspective crops from a panorama or multi-view images given depth maps and poses). Unlike prior methods that rely on iterative image warping and inpainting, MVDiffusion simultaneously generates all images with a global awareness, effectively addressing the prevalent error accumulation issue. At its core, MVDiffusion processes perspective images in parallel with a pre-trained text-to-image diffusion model, while integrating novel correspondence-aware attention layers to facilitate cross-view interactions. For panorama generation, while only trained with 10k panoramas, MVDiffusion is able to generate high-resolution photorealistic images for arbitrary texts or extrapolate one perspective image to a 360-degree view. For multi-view depth-to-image generation, MVDiffusion demonstrates state-of-the-art performance for texturing a scene mesh.<br/>Project page, https://mvdiffusion.github.io; NeurIPS 2023 (spotlight); Compressed camera-ready version<br/>