Publications (7)
Improved Scene Landmark Detection for Camera Localization
Tien Do, Sudipta N. Sinha
Camera localization methods based on retrieval, local feature matching, and 3D structure-based pose estimation are accurate but require high storage, are slow, and are not privacy-…
Surface Normal Estimation of Tilted Images via Spatial Rectifier
Tien Do, Khiem Vuong, Stergios I. Roumeliotis +1
In this paper, we present a spatial rectifier to estimate surface normals of tilted images. Tilted images are of particular interest as more visual data are captured by arbitrarily…
Egocentric Scene Understanding via Multimodal Spatial Rectifier
Tien Do, Khiem Vuong, Hyun Soo Park
In this paper, we study a problem of egocentric scene understanding, i.e., predicting depths and surface normals from an egocentric image. Egocentric scene understanding poses unpr…
Deep Multi-view Depth Estimation with Predicted Uncertainty
Tong Ke, Tien Do, Khiem Vuong +2
In this paper, we address the problem of estimating dense depth from a sequence of images using deep neural networks. Specifically, we employ a dense-optical-flow network to comput…
Deep Depth Estimation from Visual-Inertial SLAM
Kourosh Sartipi, Tien Do, Tong Ke +2
This paper addresses the problem of learning to complete a scene's depth from sparse depth points and images of indoor scenes. Specifically, we study the case in which the sparse d…
Author Name Disambiguation by Using Deep Neural Network
Hung Nghiep Tran, Tin Huynh, Tien Do
Author name ambiguity decreases the quality and reliability of information retrieved from digital libraries. Existing methods have tried to solve this problem by predefining a feat…
Ego4D: Around the World in 3,000 Hours of Egocentric Video
Kristen Grauman, Andrew Westbury, Eugene Byrne +82
We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household, outd…