Yuliang Xiu
@xiuyuliang.bsky.social
Assistant Professor @ Westlake University. PhD @ MPI-IS. Focusing on democratizing human-centric digitization.
@xingyu-chen.bsky.social experimented with the attention layers of DUSt3R and discovered that these layers encode the dynamic motions of objects and cameras!
🦣Easi3R: 4D Reconstruction Without Training!
Limited 4D datasets? Take it easy.
#Easi3R adapts #DUSt3R for 4D reconstruction by disentangling and repurposing its attention maps → make 4D reconstruction easier than ever!
🔗Page: easi3r.github.io
Limited 4D datasets? Take it easy.
#Easi3R adapts #DUSt3R for 4D reconstruction by disentangling and repurposing its attention maps → make 4D reconstruction easier than ever!
🔗Page: easi3r.github.io
April 1, 2025 at 4:04 PM
@xingyu-chen.bsky.social experimented with the attention layers of DUSt3R and discovered that these layers encode the dynamic motions of objects and cameras!
Checkout the thread of #Feat2GS, the 3D awareness of visual foundation models (VFMs) "should" and "could" be evaluated on large-scale casual video, rather than the data with 3D labels.
How much 3D do visual foundation models (VFMs) know?
Previous work requires 3D data for probing → expensive to collect!
#Feat2GS @cvprconference.bsky.social 2025 - our idea is to read out 3D Gaussains from VFMs features, thus probe 3D with novel view synthesis.
🔗Page: fanegg.github.io/Feat2GS
Previous work requires 3D data for probing → expensive to collect!
#Feat2GS @cvprconference.bsky.social 2025 - our idea is to read out 3D Gaussains from VFMs features, thus probe 3D with novel view synthesis.
🔗Page: fanegg.github.io/Feat2GS
March 31, 2025 at 4:34 PM
Checkout the thread of #Feat2GS, the 3D awareness of visual foundation models (VFMs) "should" and "could" be evaluated on large-scale casual video, rather than the data with 3D labels.
Reposted by Yuliang Xiu
How much 3D do visual foundation models (VFMs) know?
Previous work requires 3D data for probing → expensive to collect!
#Feat2GS @cvprconference.bsky.social 2025 - our idea is to read out 3D Gaussains from VFMs features, thus probe 3D with novel view synthesis.
🔗Page: fanegg.github.io/Feat2GS
Previous work requires 3D data for probing → expensive to collect!
#Feat2GS @cvprconference.bsky.social 2025 - our idea is to read out 3D Gaussains from VFMs features, thus probe 3D with novel view synthesis.
🔗Page: fanegg.github.io/Feat2GS
March 31, 2025 at 4:06 PM
How much 3D do visual foundation models (VFMs) know?
Previous work requires 3D data for probing → expensive to collect!
#Feat2GS @cvprconference.bsky.social 2025 - our idea is to read out 3D Gaussains from VFMs features, thus probe 3D with novel view synthesis.
🔗Page: fanegg.github.io/Feat2GS
Previous work requires 3D data for probing → expensive to collect!
#Feat2GS @cvprconference.bsky.social 2025 - our idea is to read out 3D Gaussains from VFMs features, thus probe 3D with novel view synthesis.
🔗Page: fanegg.github.io/Feat2GS