发表机构
Peking University（北京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
GenNVS提出一种通过解耦3D先验进行几何增强的新视角合成框架，利用3D高斯泼溅和双流掩蔽机制，提升视觉质量与几何准确性，并支持灵活场景编辑。
AI 中文摘要
单图像新视角合成仍然具有挑战性，因为潜在的3D几何高度模糊。最近的基于扩散的方法产生了合理的结果，但它们通常难以保持前景物体的几何结构和空间连贯性。我们提出了GenNVS，一个通过解耦3D先验进行几何增强新视角合成的框架。具体来说，GenNVS使用3D高斯泼溅对前景物体和背景进行建模，并通过从粗到细的几何优化过程将它们对齐，以形成统一的3D场景。该场景通过提出的双流掩蔽机制条件化视频扩散模型，该机制通过联合利用渲染有效性掩码和几何感知扭曲来引导合成。实验结果表明，GenNVS在视觉质量和几何准确性方面均优于近期方法，同时自然支持灵活的场景编辑。
英文摘要
Single-image novel view synthesis remains challenging because the underlying 3D geometry is highly ambiguous. Recent diffusion-based approaches produce plausible results, but they often struggle to preserve the geometric structure and spatial coherence of foreground objects. We present GenNVS, a framework for geometry-enhanced novel view synthesis via a disentangled 3D prior. Specifically, GenNVS models foreground objects and the background with 3D Gaussian Splatting and aligns them through a coarse-to-fine geometric optimization process to form a unified 3D scene. This scene conditions a video diffusion model through the proposed Dual-Stream Masking mechanism, which guides synthesis by jointly exploiting rendered validity masks and geometry-aware warping. Experimental results show that GenNVS performs favorably against recent methods in both visual quality and geometric accuracy, while naturally supporting flexible scene editing.
Commentsauthor errors
