Alexandre Morgand (@Almorgand)
2025-12-18 | โค๏ธ 104 | ๐ 11
โPAD3R: Pose-Aware Dynamic 3D Reconstruction from Casual Videosโ
TL;DR: canonical frame selection;image to 3D (static 3D Gaussian);set of randomly sampled camera poses to fine-tune a lightweight image2pose estimator; camera pose estimator to optimize a deformable 3d object model https://x.com/Almorgand/status/2001695549259747415/video/1
๐ ์๋ณธ ๋งํฌ
๋ฏธ๋์ด
