Khiem Vuong (@kvuongdev)
2025-06-07 | โค๏ธ 149 | ๐ 27
Ground-aerial 3D prediction is tough! @zhiwen_fan_โs work highlights the struggle for existing models (DUSt3R/MASt3R/VGGT/etc.), indicating that much work still needs to be done in this area.
At CVPR2025, we will be presenting AerialMegaDepth (https://aerial-megadepth.github.io/), a hybrid dataset combining mesh renderings with real ground images (MegaDepth) to bridge this gap.
If curious, please stop by our poster:
๐๏ธ Sunday 06/15 10:30AM ExHall D | Poster #59
์ธ์ฉ ํธ์
Zhiwen(Aaron) Fan (@zhiwen_fan_)
Discover the right 3D Geometric Foundation Model for your taskโwhether itโs stereo matching, multi-view depth estimation, video depth, pose estimation, semantic understanding, or novel view synthesis. Explore more insights in our E3DBench FoundationModel 3D GaussianSplatting.
Project Webpage: https://t.co/t4nU7FLZZH
๐ฌ ์์
