no code implementations • 22 Feb 2024 • Han Zhang, Daoping Zhang, Lok Ming Lui
In this paper, we propose the quasi-conformal interactive segmentation (QIS) model, which incorporates user input in the form of positive and negative clicks.
no code implementations • 8 Dec 2023 • Houting Li, Mengxuan Dong, Lok Ming Lui
Accurate analysis and classification of facial attributes are essential in various applications, from human-computer interaction to security systems.
no code implementations • 4 Oct 2023 • Han Zhang, Qiguang Chen, Lok Ming Lui
The QCTN is a deep neural network that outputs a quasiconformal map, which can be used to transform a geometrically distorted image into an improved version that is closer to the distribution of natural or good images.
1 code implementation • 22 Apr 2023 • Hanhui Yang, Juncheng Li, Lok Ming Lui, Shihui Ying, Jun Shi, Tieyong Zeng
To solve this problem, we propose a lightweight and accurate Edge Attention MRI Reconstruction Network (EAMRI) to reconstruct images with edge guidance.
no code implementations • 7 Oct 2022 • Han Zhang, Lok Ming Lui
Comparing to the segmentation framework based on pixel-wise classification, deformation-based segmentation models that warp a template to enclose the regions are more convenient to enforce geometric constraints.
no code implementations • 15 Aug 2022 • Yuchen Guo, Qiguang Chen, Gary P. T. Choi, Lok Ming Lui
In this work, we propose a novel framework for the automatic landmark detection and registration of brain cortical surfaces using quasi-conformal geometry and convolutional neural networks.
no code implementations • 27 Feb 2022 • Han Zhang, Lok Ming Lui
TPSN is a deformation-based model that yields a deformation map through a UNet, which takes the medical image and a template mask as inputs.
no code implementations • 20 Oct 2021 • Qiguang Chen, Zhiwen Li, Lok Ming Lui
Existing methods to solve the mapping problems are often inefficient and can sometimes get trapped in local minima.
no code implementations • 20 Oct 2021 • Daoping Zhang, Gary P. T. Choi, Jianping Zhang, Lok Ming Lui
With the advancement of computer technology, there is a surge of interest in effective mapping methods for objects in higher-dimensional spaces.
no code implementations • 31 Mar 2021 • Daoping Zhang, Lok Ming Lui
In this paper, we propose a novel 3D topology-preserving registration-based segmentation model with the hyperelastic regularization, which can handle both 2D and 3D images.
no code implementations • 30 Mar 2021 • Chenran Lin, Lok Ming Lui
The proposed signature is based on the harmonic extension of the conformal welding map of a unit circle and its Beltrami coefficient.
no code implementations • 1 Jan 2021 • Di Qiu, Zhanghan Ke, Peng Su, Lok Ming Lui
Many important problems in the real world don't have unique solutions.
no code implementations • 30 Oct 2020 • Ho Law, Gary P. T. Choi, Ka Chun Lam, Lok Ming Lui
In this paper, we develop a novel method for large deformation image registration by a fusion of quasiconformal theory and convolutional neural network (CNN).
1 code implementation • 6 Aug 2020 • Ho Law, Lok Ming Lui, Chun Yin Siu
To decompose the longitudinal deformation, we propose to carry out the low rank and sparse decomposition of the Beltrami descriptor.
no code implementations • 25 Jul 2020 • Di Qiu, Lok Ming Lui
We motivate our use of discrete latent space through the multi-modal posterior collapse problem in current conditional generative models, then develop the theoretical background, and extensively validate our method on both synthetic and realistic tasks.
no code implementations • 3 Mar 2020 • Gary P. T. Choi, Di Qiu, Lok Ming Lui
In this work, we develop a framework for shape analysis using inconsistent surface mapping.
no code implementations • 7 Jan 2019 • Gary P. T. Choi, Hei Long Chan, Robin Yong, Sarbin Ranjitkar, Alan Brook, Grant Townsend, Ke Chen, Lok Ming Lui
We deploy our framework on a dataset of human premolars to analyze the tooth shape variation among genders and ancestries.
no code implementations • 12 Jul 2018 • Wai Ho Chak, Chun Pong Lau, Lok Ming Lui
Instead of requiring a massive training sample size in deep networks, we purpose a training strategy that is based on a new data augmentation method to model turbulence from a relatively small dataset.
no code implementations • 8 Dec 2017 • Chun Pong Lau, Yu Hin Lai, Lok Ming Lui
The energy consists of a fidelity term measuring the discrepancy between the extracted image and the subsampled frames, as well as regularization terms on the extracted image and the subsample.
no code implementations • 11 Oct 2017 • Chun Pong Lau, Chun Pang Yung, Lok Ming Lui
In this paper, we propose a simple and yet effective method to resize an image, which preserves the geometry of the important content, using the Beltrami representation.
no code implementations • 11 Apr 2017 • Chun Pong Lau, Yu Hin Lai, Lok Ming Lui
The subsampled image sequence is then stabilized by applying the Robust Principal Component Analysis (RPCA) on the deformation fields between image frames and warping the image frames by a quasiconformal map associated with the low-rank part of the deformation matrix.
no code implementations • 20 May 2016 • Chun Pang Yung, Gary P. T. Choi, Ke Chen, Lok Ming Lui
For each high resolution image or video frame, we compute an optimal coarse triangulation which captures the important features of the image.
no code implementations • 20 Nov 2015 • Ting Wei Meng, Gary Pui-Tung Choi, Lok Ming Lui
Based on the discrete analogue, we propose a novel method called TEMPO for computing Teichm\"{u}ller extremal mappings between feature-endowed point clouds.
no code implementations • 30 Aug 2015 • Gary Pui-Tung Choi, Kin Tat Ho, Lok Ming Lui
In this paper, we extend a state-of-the-art spherical conformal parameterization algorithm for genus-0 closed meshes to the case of point clouds, using an improved approximation of the Laplace-Beltrami operator on data points.
no code implementations • 29 Aug 2014 • Pui Tung Choi, Lok Ming Lui
Surface parameterizations have been widely used in computer graphics and geometry processing.
no code implementations • CVPR 2014 • Wei Zeng, Lok Ming Lui, Xianfeng GU
The physically plausible constraints, in terms of feature landmarks and deformation types, define subspaces in the Beltrami coefficient space.
no code implementations • 26 Mar 2014 • Kin Tat Ho, Lok Ming Lui
QCMC computes a quasi-conformal map from a multiply-connected domain $S$ onto a punctured disk $D_S$ associated with a given Beltrami differential.