iiinova — where your digital self keeps evolving

Yue Chen

@fanegg.bsky.social

81 followers 162 following 11 posts

PhD Student at Westlake University. 3D/4D Reconstruction, Human Intelligence. fanegg.github.io

Posts Replies Media

Yue Chen @fanegg.bsky.social · 08/10/2025

#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/

120

Yue Chen @fanegg.bsky.social · 01/10/2025

Again, training-free is all you need.

030

Reposted by Yue Chen

Haiwen Huang @haiwen-huang.bsky.social · 22/04/2025

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...

0195

Reposted by Yue Chen

Andreas Geiger @andreasgeiger.bsky.social · 01/04/2025

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.

1312

Yue Chen @fanegg.bsky.social · 01/04/2025

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

040

Yue Chen @fanegg.bsky.social · 01/04/2025

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

040

Yue Chen @fanegg.bsky.social · 31/03/2025

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

1247