MultiDiff: Consistent Novel View Synthesis from a Single Image

TL;DR

MultiDiff is a new method that synthesizes consistent novel views from a single image by leveraging depth priors and video diffusion models, achieving high-quality results with improved stability and efficiency.

Contribution

It introduces a novel approach combining monocular depth and video diffusion priors for stable, multi-view consistent scene synthesis from a single image.

Findings

Outperforms state-of-the-art on RealEstate10K and ScanNet datasets.

Produces high-quality, multi-view consistent results for long-term scene generation.

Supports multi-view consistent editing without additional tuning.

Abstract

We introduce MultiDiff, a novel approach for consistent novel view synthesis of scenes from a single RGB image. The task of synthesizing novel views from a single reference image is highly ill-posed by nature, as there exist multiple, plausible explanations for unobserved areas. To address this issue, we incorporate strong priors in form of monocular depth predictors and video-diffusion models. Monocular depth enables us to condition our model on warped reference images for the target views, increasing geometric stability. The video-diffusion prior provides a strong proxy for 3D scenes, allowing the model to learn continuous and pixel-accurate correspondences across generated images. In contrast to approaches relying on autoregressive image generation that are prone to drifts and error accumulation, MultiDiff jointly synthesizes a sequence of frames yielding high-quality and multi-view consistent results -- even for long-term scene generation with large camera movements, while reducing inference time by an order of magnitude. For additional consistency and image quality improvements, we introduce a novel, structured noise distribution. Our experimental results demonstrate that MultiDiff outperforms state-of-the-art methods on the challenging, real-world datasets RealEstate10K and ScanNet. Finally, our model naturally supports multi-view consistent editing without the need for further tuning.