Tak-Wai Hui

Orcid: 0000-0002-1441-9289

According to our database1, Tak-Wai Hui authored at least 19 papers between 2010 and 2022.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2022
RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenes.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021
A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization.
IEEE Trans. Pattern Anal. Mach. Intell., 2021

2020
LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation.
Proceedings of the Computer Vision - ECCV 2020, 2020

Inter-Region Affinity Distillation for Road Marking Segmentation.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019
Learning to Synthesize Fashion Textures.
CoRR, 2019

2018
LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

2016
Depth Map Super-Resolution by Deep Multi-Scale Guidance.
Proceedings of the Computer Vision - ECCV 2016, 2016

2015
Determining shape and motion from monocular camera: A direct approach using normal flows.
Pattern Recognit., 2015

2014
Dense depth map generation using sparse depth data from normal flow.
Proceedings of the 2014 IEEE International Conference on Image Processing, 2014

Depth enhancement using RGB-D guided filtering.
Proceedings of the 2014 IEEE International Conference on Image Processing, 2014

Motion-Depth: RGB-D Depth Map Enhancement with Motion and Depth in Complement.
Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

Accelerating the Distribution Estimation for the Weighted Median/Mode Filters.
Proceedings of the Computer Vision - ACCV 2014, 2014

2013
Motion and shape from apparent flow.
PhD thesis, 2013

Determining shape and motion from non-overlapping multi-camera rig: A direct approach using normal flows.
Comput. Vis. Image Underst., 2013

Binocular estimation of motion: A least-square solution using normal flows.
Proceedings of the IEEE International Conference on Image Processing, 2013

Structure from motion directly from a sequence of binocular images without explicit correspondence establishment.
Proceedings of the IEEE International Conference on Image Processing, 2013

Determining Motion Directly from Normal Flows Upon the Use of a Spherical Eye Platform.
Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

2012
Towards a robust hand-eye calibration using normal flows.
Proceedings of the 21st International Conference on Pattern Recognition, 2012

2010
Determining Spatial Motion Directly from Normal Flow Field: A Comprehensive Treatment.
Proceedings of the Computer Vision - ACCV 2010 Workshops, 2010


  Loading...