1 code implementation • 1 May 2020 • Zhao-Yang Wang, Hongtao Wang
The adversarial attacks against deep neural networks on computer vision tasks have spawned many new technologies that help protect models from avoiding false predictions.
no code implementations • 17 Sep 2019 • Hieu Nguyen, Hui Li, Qiang Qiu, Yuzeng Wang, Zhao-Yang Wang
A robust single-shot 3D shape reconstruction technique integrating the fringe projection profilometry (FPP) technique with the deep convolutional neural networks (CNNs) is proposed in this letter.
no code implementations • 16 Sep 2019 • Zhao-Yang Wang, Xiao-Yun Zhou, Peichao Li, Celia Riga, Guang-Zhong Yang
3D shape instantiation which reconstructs the 3D shape of a target from limited 2D images or projections is an emerging technique for surgical intervention.
no code implementations • 16 Sep 2019 • Peichao Li, Xiao-Yun Zhou, Zhao-Yang Wang, Guang-Zhong Yang
Accurate volume segmentation from the Computed Tomography (CT) scan is a common prerequisite for pre-operative planning, intra-operative guidance and quantitative assessment of therapeutic outcomes in robot-assisted Minimally Invasive Surgery (MIS).
no code implementations • 21 Aug 2019 • Xiao-Yun Zhou, Peichao Li, Zhao-Yang Wang, Guang-Zhong Yang
However, two potential issues exist in BIN: first, the Clip function is not differentiable at input values of 0 and 1; second, the combined feature map is not with a normalized distribution which is harmful for signal propagation in DCNN.
no code implementations • 24 Jul 2019 • Xiao-Yun Zhou, Zhao-Yang Wang, Peichao Li, Jian-Qing Zheng, Guang-Zhong Yang
An average point cloud-to-point cloud (PC-to-PC) error of 1. 72mm has been achieved, which is comparable to the PLSR-based (1. 42mm) and KPLSR-based (1. 31mm) two-stage shape instantiation algorithm.