#Human3R: Everyone Everywhere All at Once Just input a RGB video, we online reconstruct 4D humans and scene in 𝗢𝗻𝗲 model and 𝗢𝗻𝗲 stage. Training this versatile model is easier than you think – it just takes 𝗢𝗻𝗲 day using 𝗢𝗻𝗲 GPU! 🔗Page: fanegg.github.io/Human3R/

Again, training-free is all you need.

Andreas Geiger@andreasgeiger.bsky.social · last yr.

#TTT3R: 3D Reconstruction as Test-Time Training TTT3R offers a simple state update rule to enhance length generalization for #CUT3R — No fine-tuning required! 🔗Page: rover-xingyu.github.io/TTT3R We rebuilt @taylorswift13’s "22" live at the 2013 Billboard Music Awards - in 3D!

Excited to introduce LoftUp! A strong (than ever) and lightweight feature upsampler for vision encoders that can boost performance on dense prediction tasks by 20%–100%! Easy to plug into models like DINOv2, CLIP, SigLIP — simple design, big gains. Try it out! github.com/andrehuang/l...

I was really surprised when I saw this. Dust3R has learned very well to segment objects without supervision. This knowledge can be extracted post-hoc, enabling accurate 4D reconstruction instantly.

Xingyu Chen@xingyu-chen.bsky.social · 2y ago

🦣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

Just "dissect" the cross-attention mechanism of #DUSt3R, making 4D reconstruction easier.

Xingyu Chen@xingyu-chen.bsky.social · 2y ago

💡Humans naturally separate ego-motion from object-motion without dynamic labels. We observe that #DUSt3R has implicitly learned a similar mechanism, reflected in its attention layers.

#Easi3R is a simple training-free approach adapting DUSt3R for dynamic scenes.

Xingyu Chen@xingyu-chen.bsky.social · 2y ago

🦣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

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