Ayoung

📢 Introducing GenSfM – a generic Structure-from-Motion pipeline built on COLMAP, with smooth, invertible, and universal calibration for diverse cameras — from pinhole to catadioptric! Thanks @don2qian @visionviktor @mapo1 for the great collaboration. 🔗 ivonne320.github.io/yihan.home/Gen…

Visual SLAM has made major success in static scenes — now let’s explore the dynamic world we live in! At #CVPR2025, we introduce 4DTAM, 4D Tracking & Mapping using dynamic surface Gaussians optimized through diff. rendering. muskie82.github.io/4dtam/ w/ @BaeGwangbin @AjdDavison

It was a great pleasure to visit @WHOI and give a talk at the AOPE seminar. Grateful to @robobzbz for coordinating the talk.

Two papers accepted for #ICCV2025! Yay!

Joined as a panel to have a fruitful discussion on the past, present and the future of robotics at RSS 2025!

New IF and ranking. RA-L Q2->Q1 and IJRR Q1->Q2. jcr.clarivate.com/jcr/

What if a Transformer could render? Not text → image. But mesh → image — with global illumination. No rasterizers. No ray-tracers. Just a Transformer without per-scene training. RenderFormer does exactly that. #SIGGRAPH2025 🔗microsoft.github.io/renderformer

AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views @jiang_juanan, Yucheng Mao, @EvenEveno, @isaac__lt, Kerui Ren, Yichen Jin, Xudong Xu, Mulin Yu, @pangjiangmiao, Feng Zhao, @lindahua, @doubledaibo tl;dr: VGGT->base & geometry priors arxiv.org/abs/2505.23716

ICRA is toward the end. Our group did a great job presenting 2 RAL, 6 ICRA, 3 workshops, 1 LBR. Kudos to all!

With two SLAM legends — soon to write the foreword of the SLAM Handbook! 🤖📕

SNU robotics at ICRA!

Amazing. Seamlessly walk, perceive, approach, and socialize.

Thank you very much for joining us at ICRA! Here is our thermal group photo from the workshop 🎉 🎯Our group also releases the TIR project page with essential modules for TIR. rpm-robotics-lab.github.io/tirgroup/

All three parts of the SLAM handbook are finally available to the public.