Noah Snavely

snavely.bsky.social

15 March 2026 17:07

At kids' parties a lot of dads go in for a "clap shake" type greeting. Was I supposed to learn how to do this at some point?

Noah Snavely

snavely.bsky.social

19 February 2025 15:28

I think Qianqian et al's work is really cool! The problem of modeling state within a 3D reasoning system is quite interesting. (And I believe it's pronounced "cuter".)

Dmytro Mishkin

ducha-aiki.bsky.social

22 November 2024 01:38

Generating 3D-Consistent Videos from Unposed Internet Photos Gene Chou, Kai Zhang, Sai Bi, Hao Tan, Zexiang Xu, Fujun Luan, Bharath Hariharan, @snavely.bsky.social tl;dr: multiview CroCo meets diffusion (DiT). Better than luma? arxiv.org/abs/2411.13549

Gene Chou

gene-chou.bsky.social

22 November 2024 01:38

We've released our paper "Generating 3D-Consistent Videos from Unposed Internet Photos"! Video models like Luma generate pretty videos, but sometimes struggle with 3D consistency. We can do better by scaling them with 3D-aware objectives. 1/N page: genechou.com/kfcw

Morris Alper

malper.bsky.social

22 November 2024 01:37

Cross-posting our recent work from this #ECCV2024! CLIP shows emergent understanding of *visual-semantic hierarchies*. Our benchmark *HierarCaps* gives GT to measure and further align this! Project page: hierarcaps.github.io Paper: arxiv.org/abs/2407.08521