VGGT-Diff:视觉几何与扩散模型相结合的稀疏视角新视角合成
TLDR
VGGT-Diff将VGGT-Ω的几何潜变量注入视频扩散模型,提升稀疏视角新视角合成的插值与外推。
评分理由
The paper presents a strong integration of geometric reconstruction with generative diffusion for novel view synthesis, with experiments showing competitive results. However, it does not position itself as a world model or focus on world dynamics, limiting relevance to those keywords.
Read-first 评分解释
综合优先阅读分 19,由主题、引用、图谱、方法、可复现性和近期性等信号加权得到。 原始总分保留为 5。
研究版图角色
前沿论文
排序敏感性
稳定性:volatile;排名波动范围:62。