Peiyun Hu

I am a PhD student (2016-) at the Robotics Institute of Carnegie Mellon University, advised by with Deva Ramanan. I spent 2 years at UC Irvine and 4 years at Tsinghua University.


What You See is What You Get: Exploiting Visibility for 3D Object Detection
Peiyun Hu, Jason Ziglar, David Held, Deva Ramanan
Computer Vision and Pattern Recognition (CVPR), 2020
(Oral Presentation)
preprint / project / slides / talk / video

We exploit often overlooked freespace in LiDAR-based 3D object detection.


Learning to Optimally Segment Point Clouds
Peiyun Hu, David Held*, Deva Ramanan*
IEEE Robotics and Automation Letters (RA-L) and ICRA, 2020
paper / project / slides / talk / video / code

We marry graph search with learning for point cloud optimal segmentation.


Active Learning with Partial Feedback
Peiyun Hu, Zack C. Lipton, Anima Anandkumar, Deva Ramanan
International Conference on Learning Representations (ICLR), 2019
paper / poster

We formulate AL as a 20Q game between evolving models and human.


Finding Tiny Faces
Peiyun Hu, Deva Ramanan
Computer Vision and Pattern Recognition (CVPR), 2017
paper / project / video / poster / press / code

We address key challenges in detecting tiny objects with neural nets.


Bottom-Up and Top-Down Reasoning with Hierarchical Rectified Gaussians
Peiyun Hu, Deva Ramanan
Computer Vision and Pattern Recognition (CVPR), 2016
(Spotlight Presentation)
paper / project / ext. abstract / slides / talk / poster / code

We derive architectures to endow neural nets with top-down reasoning.

Web design inspired by Jon Barron