MultiDiff: Consistent Novel View Synthesis from a Single Image

• Main Authors: Muller, Norman, Schwarz, Katja, Rossle, Barbara, Porzi, Lorenzo, Bulo, Samuel Rota, NieBner, Matthias, Kontschieder, Peter
• Format: Conference Proceeding
• Language: English
• Subjects: Cameras; Diffusion; Image synthesis; Multi-view Consistency; Noise; Predictive models; Scene Synthesis; Solid modeling; Stability analysis; Three-dimensional displays
• ISSN: 2575-7075
• DOI: 10.1109/CVPR52733.2024.00977

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.