activity
20172022
most citedFast, Autonomous Flight in GPS-Denied and Cluttered Environments

202 citations · 210 across the 4 of their papers we have counts for

collaborators

11 papers

cs.CV2022

Instance Segmentation with Cross-Modal Consistency

Alex Zihao Zhu, Vincent Casser, Reza Mahjourian +2

Segmenting object instances is a key task in machine perception, with safety-critical applications in robotics and autonomous driving. We introduce a novel approach to instance seg…

cs.NE2020

Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks

Chankyu Lee, Adarsh Kumar Kosta, Alex Zihao Zhu +3

Event-based cameras display great potential for a variety of tasks such as high-speed motion detection and navigation in low-light environments where conventional frame-based camer…

cs.CV2019

EventGAN: Leveraging Large Scale Image Datasets for Event Cameras

Alex Zihao Zhu, Ziyun Wang, Kaung Khant +1

Event cameras provide a number of benefits over traditional cameras, such as the ability to track incredibly fast motions, high dynamic range, and low power consumption. However, t…

cs.CV20195 cited

Motion Equivariant Networks for Event Cameras with the Temporal Normalization Transform

Alex Zihao Zhu, Ziyun Wang, Kostas Daniilidis

In this work, we propose a novel transformation for events from an event camera that is equivariant to optical flow under convolutions in the 3-D spatiotemporal domain. Events are…

cs.CV20183 cited

Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion

Alex Zihao Zhu, Liangzhe Yuan, Kenneth Chaney +1

In this work, we propose a novel framework for unsupervised learning for event cameras that learns motion information from only the event stream. In particular, we propose an input…

cs.CV2018

Robustness Meets Deep Learning: An End-to-End Hybrid Pipeline for Unsupervised Learning of Egomotion

Alex Zihao Zhu, Wenxin Liu, Ziyun Wang +2

In this work, we propose a method that combines unsupervised deep learning predictions for optical flow and monocular disparity with a model based optimization procedure for instan…