Search papers, labs, and topics across Lattice.
This paper introduces MetaView, a novel diffusion-based framework for monocular novel view synthesis that effectively combines implicit geometry modeling with essential explicit 3D cues. By leveraging a feed-forward geometry perception network and metric depth, MetaView achieves both geometry consistency and precise camera control, overcoming the limitations of existing methods that either lack spatial coherence or restrict generalization. Experimental results show that MetaView significantly outperforms current approaches in generating high-quality images under large viewpoint changes, demonstrating its superior generalization capabilities.
Achieving both geometry consistency and precise controllability, MetaView outperforms existing methods in monocular novel view synthesis under challenging conditions.
Current visual generation models are capable of producing high-quality content, yet they lack a coherent perception of the spatial structure. Existing generative novel view synthesis methods typically introduce explicit geometry priors, which enforce spatial consistency but inherently restrict generalization in large view changes. In contrast, recent interactive generative methods favor implicit scene modeling, offering greater flexibility at the cost of precise camera control and geometry consistency. In this paper, we propose MetaView, a diffusion-based monocular novel view synthesis framework that enables rendering under large view changes from a single image. Our key insight is to combine implicit geometry modeling with minimal yet essential explicit 3D cues: we incorporate implicit geometry priors from a feed-forward geometry perception network to regularize structure without imposing restrictive reconstruction pipelines, while leveraging metric depth to anchor the generation to a metric scale. This design allows MetaView to achieve both geometry consistency and precise controllability. Extensive experiments demonstrate that, under challenging monocular large viewpoint changes, MetaView significantly outperforms existing methods and exhibits superior generalization. Our code is publicly available at https://github.com/KlingAIResearch/MetaView.
