Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion
This addresses the challenge of generating consistent 3D views from limited inputs for applications in computer vision and graphics, representing a novel method rather than an incremental improvement.
The paper tackles the problem of 3D scene reconstruction from sparse posed images by introducing MVGD, a diffusion-based architecture that directly generates images and depth maps from novel viewpoints, achieving state-of-the-art results in novel view synthesis and depth estimation benchmarks.
Current methods for 3D scene reconstruction from sparse posed images employ intermediate 3D representations such as neural fields, voxel grids, or 3D Gaussians, to achieve multi-view consistent scene appearance and geometry. In this paper we introduce MVGD, a diffusion-based architecture capable of direct pixel-level generation of images and depth maps from novel viewpoints, given an arbitrary number of input views. Our method uses raymap conditioning to both augment visual features with spatial information from different viewpoints, as well as to guide the generation of images and depth maps from novel views. A key aspect of our approach is the multi-task generation of images and depth maps, using learnable task embeddings to guide the diffusion process towards specific modalities. We train this model on a collection of more than 60 million multi-view samples from publicly available datasets, and propose techniques to enable efficient and consistent learning in such diverse conditions. We also propose a novel strategy that enables the efficient training of larger models by incrementally fine-tuning smaller ones, with promising scaling behavior. Through extensive experiments, we report state-of-the-art results in multiple novel view synthesis benchmarks, as well as multi-view stereo and video depth estimation.