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.

Research
teaser_vis

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.

teaser_seg

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.

teaser_alpf

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.

teaser_tiny

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.

teaser_topdown

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