用于视频预测和填充的扩散模型
TLDR
RaMViD通过3D卷积和掩码将扩散模型扩展到视频,实现最先进的视频预测和填充。
评分理由
The paper introduces a novel conditioning technique for video diffusion models, achieving state-of-the-art results on benchmark datasets. However, it focuses narrowly on video prediction and infilling without explicit connection to world models or reinforcement learning, limiting its scope.
Read-first 评分解释
综合优先阅读分 32.1,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 9。
研究版图角色
候选论文
排序敏感性
稳定性:volatile;排名波动范围:49。