Scholar
Peiyun Hu
Google Scholar ID: SEAowdYAAAAJ
Apple
Citations & Impact
Citations
1,425
H-index
14
i10-index
14
Publications
20
Co-authors
21
list available
Publications
Resume (English only)
Academic Achievements
- CoMotion: Concurrent Multi-person 3D Motion, ICLR, 2025
- Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting, CVPR, 2023
- Differentiable Raycasting for Self-Supervised Planning, ECCV, 2022
- Safe Local Motion Planning with Self-Supervised Freespace Forecasting, CVPR, 2021
- Active Perception using Light Curtains for Autonomous Driving, ECCV, 2020 (Spotlight Presentation)
- What You See is What You Get: Exploiting Visibility for 3D Object Detection, CVPR, 2020 (Oral Presentation)
- Learning to Optimally Segment Point Clouds, RA-L and ICRA, 2020
- Recognizing Tiny Faces, CVPR-W, 2019
- Inferring Distributions Over Depth from a Single Image, IROS, 2019
- Active Learning with Partial Feedback, ICLR, 2019
- Camera-based Semantic Enhanced Vehicle Segmentation for Planar LIDAR, ISTC, 2018
- Comparing Apples and Oranges: Off-Road Pedestrian Detection on the NREC Agricultural Person-Detection Dataset, JFR, 2018
- Unconstrained Face Detection and Open-Set Face Recognition Challenge, IJCB, 2017
- Finding Tiny Faces, CVPR, 2017
Research Experience
- Currently a research scientist at Apple, working with Vladlen Koltun. Previously worked at Argo AI and later at Apple SPG.
Education
- Ph.D. in Robotics from Carnegie Mellon University Robotics Institute, advised by Deva Ramanan.
Background
- Research Interests: Intersection of computer vision and robotics, exploring how machines can perceive and anticipate the world around them. Focus: From recognizing subtle visual details to reasoning about 3D structure and anticipating how the world unfolds over time.
