Qianqian Wang
qianqianwang.bsky.social
Qianqian Wang
@qianqianwang.bsky.social
Thanks to the amazing team
Yifei Zhang, @holynski.bsky.social, Alexei A. Efros, and Angjoo Kanazawa!
February 18, 2025 at 5:03 PM
From the state you can also predict unseen parts. This also improves as you see more.
February 18, 2025 at 5:03 PM
Key insight is to store 3D information in a latent persistent state that gets continuously updated as images come in. This enables it to continuously refine its predictions as it sees more images!
February 18, 2025 at 5:03 PM