Nikolaos Sarafianos
@sarafianosn.bsky.social
Research Scientist at Meta Reality Labs working on 3D GenAI
Our novel representation makes it effortless to leverage foundational 2D models, such as diffusion models, to directly generate 3DGS.
Work with colleagues at Brown and Meta Reality Labs
Work with colleagues at Brown and Meta Reality Labs
February 6, 2025 at 3:22 PM
Our novel representation makes it effortless to leverage foundational 2D models, such as diffusion models, to directly generate 3DGS.
Work with colleagues at Brown and Meta Reality Labs
Work with colleagues at Brown and Meta Reality Labs
UVGS enables the application of image-based models for 3DGS feature extraction by representing it as multi-channel images.
We demonstrate effective compression of heterogeneous UVGS features and successful generalization of pre-trained 2D VAEs to this new representation.
We demonstrate effective compression of heterogeneous UVGS features and successful generalization of pre-trained 2D VAEs to this new representation.
February 6, 2025 at 3:22 PM
UVGS enables the application of image-based models for 3DGS feature extraction by representing it as multi-channel images.
We demonstrate effective compression of heterogeneous UVGS features and successful generalization of pre-trained 2D VAEs to this new representation.
We demonstrate effective compression of heterogeneous UVGS features and successful generalization of pre-trained 2D VAEs to this new representation.
Thank you @miniemeyer.bsky.social for sharing this, lots of familiar folks in there.
@chrisoffner3d.bsky.social if you could kindly add me to the list as well it’d be lovely. I spent most of my time on 3D generative models these days :)
@chrisoffner3d.bsky.social if you could kindly add me to the list as well it’d be lovely. I spent most of my time on 3D generative models these days :)
January 15, 2025 at 4:53 AM
Thank you @miniemeyer.bsky.social for sharing this, lots of familiar folks in there.
@chrisoffner3d.bsky.social if you could kindly add me to the list as well it’d be lovely. I spent most of my time on 3D generative models these days :)
@chrisoffner3d.bsky.social if you could kindly add me to the list as well it’d be lovely. I spent most of my time on 3D generative models these days :)
At test-time given a 3D mesh, some image guidance with the desired edit, and a coarse 3D mask, it generates the edited 3D mesh in seconds.
Work with William Gao, Dilin Wang, Yuchen Fan, Aljaž Božič, Tuur Stuyck, Zhengqin Li, Zhao Dong and Rakesh Ranjan
Work with William Gao, Dilin Wang, Yuchen Fan, Aljaž Božič, Tuur Stuyck, Zhengqin Li, Zhao Dong and Rakesh Ranjan
December 17, 2024 at 5:20 PM
At test-time given a 3D mesh, some image guidance with the desired edit, and a coarse 3D mask, it generates the edited 3D mesh in seconds.
Work with William Gao, Dilin Wang, Yuchen Fan, Aljaž Božič, Tuur Stuyck, Zhengqin Li, Zhao Dong and Rakesh Ranjan
Work with William Gao, Dilin Wang, Yuchen Fan, Aljaž Božič, Tuur Stuyck, Zhengqin Li, Zhao Dong and Rakesh Ranjan
By leveraging the representation power of large reconstruction models, we've developed a new 3D-consistent multi-view masking strategy that allows us to train our model to learn to fill in missing 3D information.
December 17, 2024 at 5:20 PM
By leveraging the representation power of large reconstruction models, we've developed a new 3D-consistent multi-view masking strategy that allows us to train our model to learn to fill in missing 3D information.