-
Article
Probabilistic-Based Feature Embedding of 4-D Light Fields for Compressive Imaging and Denoising
The high-dimensional nature of the 4-D light field (LF) poses great challenges in achieving efficient and effective feature embedding, that severely impacts the performance of downstream tasks. To tackle this ...
-
Article
A Comprehensive Study of the Robustness for LiDAR-Based 3D Object Detectors Against Adversarial Attacks
Recent years have witnessed significant advancements in deep learning-based 3D object detection, leading to its widespread adoption in numerous applications. As 3D object detectors become increasingly crucial ...
-
Article
Unsupervised video-based action recognition using two-stream generative adversarial network
Video-based action recognition faces many challenges, such as complex and varied dynamic motion, spatio-temporal similar action factors, and manual labeling of archived videos over large datasets. How to extra...
-
Article
GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation
The inherent ambiguity in ground-truth annotations of 3D bounding boxes, caused by occlusions, signal missing, or manual annotation errors, can confuse deep 3D object detectors during training, thus deteriorat...
-
Article
RegGeoNet: Learning Regular Representations for Large-Scale 3D Point Clouds
Deep learning has proven an effective tool for 3D point cloud processing. Currently, most deep set architectures are developed for sparse inputs (typically with a few thousand points), which are unable to prov...
-
Chapter and Conference Paper
DRLFNet: A Dense-Connection Residual Learning Neural Network for Light Field Super Resolution
Light field records both spatial and angular information of light rays. By using light field cameras, 3D scenes can be reconstructed easily for further virtual reality applications. Limited by the sensor size,...
-
Chapter and Conference Paper
PUGeo-Net: A Geometry-Centric Network for 3D Point Cloud Upsampling
In this paper, we propose a novel deep neural network based method, called PUGeo-Net, for upsampling 3D point clouds. PUGeo-Net incorporates discrete differential geometry into deep learning elegantly by learn...
-
Chapter and Conference Paper
Deep Spatial-Angular Regularization for Compressive Light Field Reconstruction over Coded Apertures
Coded aperture is a promising approach for capturing the 4-D light field (LF), in which the 4-D data are compressively modulated into 2-D coded measurements that are further decoded by reconstruction algorithm...
-
Chapter and Conference Paper
Fast Light Field Reconstruction with Deep Coarse-to-Fine Modeling of Spatial-Angular Clues
Densely-sampled light fields (LFs) are beneficial to many applications such as depth inference and post-capture refocusing. However, it is costly and challenging to capture them. In this paper, we propose a le...
-
Chapter and Conference Paper
Random Forest with Suppressed Leaves for Hough Voting
Random forest based Hough-voting techniques have been widely used in a variety of computer vision problems. As an ensemble learning method, the voting weights of leaf nodes in random forest play critical role ...
-
Article
Motion capture data recovery using skeleton constrained singular value thresholding
Motion capture data could be missing due to imperfections during the acquisition process. Singular value thresholding (SVT) is an effective method to recover missing motion capture data. However, its effective...