Andrew Y. Guo

I'm a PhD student studying Computer Science at the University of Toronto, supervised by David Lindell and Kyros Kutulakos.

Previously, I was an intern at Nvidia, where I was fortunate to have worked with Stan Birchfield and Bowen Wen on 3D vision and object pose estimation. I received my Bachelors of Software Engineering from the University of Waterloo.

Email:
yk[last_name] [at] cs [dot] toronto [dot] edu


Resume  /  Google Scholar  /  Twitter  /  Github

profile photo

Research

I'm interested in agentic AI and computer vision.

Dark3R: Learning SfM in the Dark
Andrew Y. Guo, Anagh Malik, SaiKiran Tedla, Yutong Dai, Yiqian Qin, Zach Salehe, Benjamin Attal, Sotiris Nousias, Kiriakos N. Kutulakos, David B. Lindell
CVPR, 2026 (Highlight)
project page / arXiv

Framework for 3D reconstruction in ultra-low-light conditions (< -4dB SNR) for the first time, with no 3D supervision required.

BOP 2024 image
BOP Challenge 2024 on Model-free, Model-based Detection, and Pose Estimation of Unseen Rigid Objects
Van Nguyen Nguyen, Stephen Tyree, Andrew Y. Guo, Médéric Fourmy, Anas Gouda, Taeyeop Lee, Sungphill Moon, Hyeontae Son, Lukas Ranftl, Jonathan Tremblay, Eric Brachmann, Bertram Drost, Vincent Lepetit, Carsten Rother, Stan Birchfield, Jiri Matas, Yann Labbé, Martin Sundermeyer, Tomáš Hodaň,
CVPR CV4MR Workshop, 2025 (Best Paper Award)
project page / arXiv

The report of BOP Challenge 2024 on model-based and model-free 2D/6D object detection on BOP-Classic and new BOP-H3 datasets (HOT3D, HOPEv2, HANDAL).

HANDAL: A Dataset of Real-World Manipulable Object Categories with Pose Annotations, Affordances, and Reconstructions
Andrew Y. Guo, Bowen Wen, Jianhe Yuan, Jonathan Tremblay, Stephen Tyree, Jeffrey Smith, Stan Birchfield
IROS, 2023  
project page / arXiv

An automated, accurate annotation tool and large, non-crowdsourced dataset with high-quality 3D annotations, pose labels, and affordances.


Source code based on Jon Barron's website.