Ruojin Cai (@ruojin8)
2024-12-23 | โค๏ธ 221 | ๐ 34
๐คCan Generative Video Models Help Pose Estimation? โ Yes! We find that generative video models can hallucinate plausible intermediate frames that provide useful context for pose estimators (e.g. DUSt3R), especially for images with little to no overlap. ๐ https://inter-pose.github.io/ https://x.com/ruojin8/status/1871248939405676810/photo/1
๋ฏธ๋์ด
