Iro Armeni (@ir0armeni)
2025-02-27 | โค๏ธ 145 | ๐ 25
How do you align point clouds, CAD, floor plans. images, and text to share scene knowledge? CrossOver learns a unified, modality-agnostic embedding spaceโenabling seamless multi-modal scene alignment without semantic labels.
CVPR2025 ๐https://sayands.github.io/crossover/ https://x.com/ir0armeni/status/1895214150504325184/video/1
๐ ์๋ณธ ๋งํฌ
๋ฏธ๋์ด
![]()
๐ Related
Auto-generated - needs manual review
์ธ์ฉ ํธ์
Sayan Deb Sarkar (@debsarkar_sayan)
๐ Excited to share our latest work, CrossOver: 3D Scene Cross-Modal Alignment, accepted to CVPR2025 ๐โจ
We learn a unified, modality-agnostic embedding space, enabling seamless scene-level alignment across multiple modalities โ no semantic annotations needed!๐ https://t.co/CODXaMOWEI
๐ฌ ์์