14 citations · 96 across the 23 of their papers we have counts for
7 papers · 1 filter
Toward Efficient Visual Gyroscopes: Spherical Moments, Harmonics Filtering, and Masking Techniques for Spherical Camera Applications
Yao Du, Carlos M. Mateo, Mirjana Maras +5
Unlike a traditional gyroscope, a visual gyroscope estimates camera rotation through images. The integration of omnidirectional cameras, offering a larger field of view compared to…
Are All Vision Models Created Equal? A Study of the Open-Loop to Closed-Loop Causality Gap
Mathias Lechner, Ramin Hasani, Alexander Amini +3
There is an ever-growing zoo of modern neural network models that can efficiently learn end-to-end control from visual observations. These advanced deep models, ranging from convol…
V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction
Tsun-Hsuan Wang, Sivabalan Manivasagam, Ming Liang +4
In this paper, we explore the use of vehicle-to-vehicle (V2V) communication to improve the perception and motion forecasting performance of self-driving vehicles. By intelligently…
3D LiDAR and Stereo Fusion using Stereo Matching Network with Conditional Cost Volume Normalization
Tsun-Hsuan Wang, Hou-Ning Hu, Chieh Hubert Lin +3
The complementary characteristics of active and passive depth sensing techniques motivate the fusion of the Li-DAR sensor and stereo camera for improved depth perception. Instead o…
Point-to-Point Video Generation
Tsun-Hsuan Wang, Yen-Chi Cheng, Chieh Hubert Lin +2
While image manipulation achieves tremendous breakthroughs (e.g., generating realistic faces) in recent years, video generation is much less explored and harder to control, which l…
Liquid Pouring Monitoring via Rich Sensory Inputs
Tz-Ying Wu, Juan-Ting Lin, Tsun-Hsuang Wang +3
Humans have the amazing ability to perform very subtle manipulation task using a closed-loop control system with imprecise mechanics (i.e., our body parts) but rich sensory informa…
Omnidirectional CNN for Visual Place Recognition and Navigation
Tsun-Hsuan Wang, Hung-Jui Huang, Juan-Ting Lin +3
Visual place recognition is challenging, especially when only a few place exemplars are given. To mitigate the challenge, we consider place recognition method using omnidirectio…