发表机构
Nanyang Technological University; Kolors Team, Kuaishou Technology; The Hong Kong University of Science and Technology (Guangzhou)（南洋理工大学; 快手科技色彩团队; 香港科技大学（广州））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究提出MetaView框架，结合隐式几何建模与少量显式3D线索，利用前馈几何感知网络隐式几何先验及度量深度，实现大视角下单目新视图合成，实验证明该方法在挑战性场景中显著优于现有方法且泛化能力强。
AI 中文摘要
当前视觉生成模型能生成高质量内容，但缺乏对空间结构的连贯感知。现有生成新视图合成方法通常引入显式几何先验，虽能保证空间一致性，但在大视角变化时泛化性受限。近期交互式生成方法倾向于隐式场景建模，灵活性高但牺牲了精确相机控制和几何一致性。本文提出MetaView，一种基于扩散的单目新视图合成框架，能从单张图像进行大视角变化下的渲染。关键在于将隐式几何建模与最少但必要的显式3D线索相结合，利用前馈几何感知网络的隐式几何先验来规范结构，同时利用度量深度将生成锚定到度量尺度。大量实验表明，在具有挑战性的单目大视角变化下，MetaView显著优于现有方法并展现出卓越的泛化能力。
英文摘要
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.
Commentsaccepted to ECCV 2026
