How much 3D do visual foundation models (VFMs) know?

Previous work requires 3D data for probing → expensive to collect!

#Feat2GS @CVPR 2025 - our idea is to read out 3D Gaussains from VFMs features, thus probe 3D with novel view synthesis.

Satori: Towards Proactive AR Assistant with Belief-Desire-Intention User Modeling
arxiv.org

杭城往事

干了九年终于达到了 ARKit 和 ARCore 的水平

能够午睡的中午的午睡前的这段时光，对于中年人在职场的作用，等同于回家前在车里抽一根烟。

加班伴侣剧，有李李，有王大锤，有郑梓妍，还有演技进步的二公主

Transfer media from Mac to Vision

人可以抠，但不可以蠢