Kwang Moo Yi (@kwangmoo_yi)
2026-01-15 | โค๏ธ 100 | ๐ 8
Sucar and Insafutdinov et al., โV-DPM: 4D Video Reconstruction with Dynamic Point Mapsโ
VGGT + time-conditioned point map estimates. Similar to Monst3r, but with VGGT. Trained to map to a canonical view, and static points live at a โcanonical timeโ. https://x.com/kwangmoo_yi/status/2011896674634146133/video/1
๐ ์๋ณธ ๋งํฌ
๋ฏธ๋์ด
๐ Related
Auto-generated - needs manual review