rsasaki0109 (@rsasaki0109)
2025-12-26 | โค๏ธ 89 | ๐ 14
E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training https://github.com/QitaoZhao/E-RayZer https://x.com/rsasaki0109/status/2004695846965968932/video/1
๐ ์๋ณธ ๋งํฌ
๋ฏธ๋์ด
๐ Related
- no-3d-representations-are-a-terrible-way-of-maintaining
- neoverse-enhancing-4d-world-model-with-in-the-wild
- wu-et-al-from-rays-to-projections-better-inputs-for-feed
- xie-et-al-lavr-scene-latent-conditioned-generative-video
- sucar-and-insafutdinov-et-al-v-dpm-4d-video-reconstruction