VGGT-World:将VGGT转化为自回归几何世界模型
TLDR
VGGT-World将冻结VGGT特征作为自回归潜状态,免去视频生成,直接预测几何深度,在KITTI等基准上高效且更优。
评分理由
The paper introduces a novel geometry world model that avoids video generation by predicting latent GFM token trajectories, with technical contributions addressing flow matching collapse and exposure bias. Strengths include strong empirical results and efficiency, but the abstract focuses mainly on depth forecasting and lacks evidence of broader interactive or generative capabilities.
Read-first 评分解释
综合优先阅读分 46.3,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 26。
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:609。