Kwang Moo Yi (@kwangmoo_yi)
2025-07-03 | ❤️ 101 | 🔁 14
Preprint of (not) today: Ma et al., “Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction” — https://jiahao-ma.github.io/puzzles/
Simple and effective idea. Crop and warp to different views (with incompletions) for data augmentation — more 3D supervision. https://x.com/kwangmoo_yi/status/1940825639189393874/video/1
🔗 Related
See similar notes in domain-vision-3d