Search Results - "Wu, Huikai"

Fast End-to-End Trainable Guided Filter by Huikai Wu, Shuai Zheng, Junge Zhang, Kaiqi Huang

“…Image processing and pixel-wise dense prediction have been advanced by harnessing the capabilities of deep learning. One central issue of deep learning is the…”
Get full text

Fast A3RL: Aesthetics-Aware Adversarial Reinforcement Learning for Image Cropping by Li, Debang, Wu, Huikai, Zhang, Junge, Huang, Kaiqi

“…Image cropping aims at improving the quality of images by removing unwanted outer areas, which is widely used in the photography and printing industry. Most of…”
Get full text

A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping by Li, Debang, Wu, Huikai, Zhang, Junge, Huang, Kaiqi

“…Image cropping aims at improving the aesthetic quality of images by adjusting their composition. Most weakly supervised cropping methods (without bounding box…”
Get full text

SparseMask: Differentiable Connectivity Learning for Dense Image Prediction by Wu, Huikai, Zhang, Junge, Huang, Kaiqi

“…In this paper, we aim at automatically searching an efficient network architecture for dense image prediction. Particularly, we follow the encoder-decoder…”
Get full text

YOLOrtho -- A Unified Framework for Teeth Enumeration and Dental Disease Detection by Mei, Shenxiao, Ma, Chenglong, Shen, Feihong, Wu, Huikai

“…Detecting dental diseases through panoramic X-rays images is a standard procedure for dentists. Normally, a dentist need to identify diseases and find the…”
Get full text

PX2Tooth: Reconstructing the 3D Point Cloud Teeth from a Single Panoramic X-ray by Ma, Wen, Wu, Huikai, Xiao, Zikai, Feng, Yang, Wu, Jian, Liu, Zuozhu

“…Reconstructing the 3D anatomical structures of the oral cavity, which originally reside in the cone-beam CT (CBCT), from a single 2D Panoramic X-ray(PX)…”
Get full text

Point Cloud Super Resolution with Adversarial Residual Graph Networks by Wu, Huikai, Zhang, Junge, Huang, Kaiqi

“…Point cloud super-resolution is a fundamental problem for 3D reconstruction and 3D data understanding. It takes a low-resolution (LR) point cloud as input and…”
Get full text

SparseMask: Differentiable Connectivity Learning for Dense Image Prediction by Wu, Huikai, Zhang, Junge, Huang, Kaiqi

“…In this paper, we aim at automatically searching an efficient network architecture for dense image prediction. Particularly, we follow the encoder-decoder…”
Get full text

FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation by Wu, Huikai, Zhang, Junge, Huang, Kaiqi, Liang, Kongming, Yu, Yizhou

“…Modern approaches for semantic segmentation usually employ dilated convolutions in the backbone to extract high-resolution feature maps, which brings heavy…”
Get full text

Fast End-to-End Trainable Guided Filter by Wu, Huikai, Zheng, Shuai, Zhang, Junge, Huang, Kaiqi

“…Dense pixel-wise image prediction has been advanced by harnessing the capabilities of Fully Convolutional Networks (FCNs). One central issue of FCNs is the…”
Get full text

MSC: A Dataset for Macro-Management in StarCraft II by Wu, Huikai, Zong, Yanqi, Zhang, Junge, Huang, Kaiqi

“…Macro-management is an important problem in StarCraft, which has been studied for a long time. Various datasets together with assorted methods have been…”
Get full text

AI-enabled Automatic Multimodal Fusion of Cone-Beam CT and Intraoral Scans for Intelligent 3D Tooth-Bone Reconstruction and Clinical Applications by Hao, Jin, Liu, Jiaxiang, Li, Jin, Pan, Wei, Chen, Ruizhe, Xiong, Huimin, Sun, Kaiwei, Lin, Hangzheng, Liu, Wanlu, Ding, Wanghui, Yang, Jianfei, Hu, Haoji, Zhang, Yueling, Feng, Yang, Zhao, Zeyu, Wu, Huikai, Zheng, Youyi, Fang, Bing, Liu, Zuozhu, Zhao, Zhihe

“…A critical step in virtual dental treatment planning is to accurately delineate all tooth-bone structures from CBCT with high fidelity and accurate anatomical…”
Get full text

A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping by Li, Debang, Wu, Huikai, Zhang, Junge, Huang, Kaiqi

“…Image cropping aims at improving the aesthetic quality of images by adjusting their composition. Most weakly supervised cropping methods (without bounding box…”
Get full text

GP-GAN: Towards Realistic High-Resolution Image Blending by Wu, Huikai, Zheng, Shuai, Zhang, Junge, Huang, Kaiqi

“…It is common but challenging to address high-resolution image blending in the automatic photo editing application. In this paper, we would like to focus on…”
Get full text