Search Results for author:
Found 9 papers, 1 papers with code
Sparse-to-Dense Depth Completion Revisited: Sampling Strategy and Graph Construction
Depth completion is a widely studied problem of predicting a dense depth map from a sparse set of measurements and a single RGB image.
Spatiotemporal Disentanglement of Arteriovenous Malformations in Digital Subtraction Angiography
Although Digital Subtraction Angiography (DSA) is the most important imaging for visualizing cerebrovascular anatomy, its interpretation by clinicians remains difficult.
Distributionally Robust Transfer Learning
Many existing transfer learning methods rely on leveraging information from source data that closely resembles the target data.
GIMM: InfoMin-Max for Automated Graph Contrastive Learning
Many GCL methods with automated data augmentation face the risk of insufficient information as they fail to preserve the essential information necessary for the downstream task.
Rate-Distortion Optimization With Alternative References For UGC Video Compression
We proposed a geometric criterion for saturation detection that works with rate-distortion optimization, and only requires a few frames from the UGC video.
Compression of user generated content using denoised references
UGC video is uploaded by users, and then it is re-encoded to be made available at various levels of quality.
Deformable Kernel Convolutional Network for Video Extreme Super-Resolution
Thanks to newly designed Deformable Kernel Convolution Alignment (DKC_Align) and Deformable Kernel Spatial Attention (DKSA) modules, DKSAN can better exploit both spatial and temporal redundancies to facilitate the information propagation across different layers.
AIM 2020 Challenge on Video Extreme Super-Resolution: Methods and Results
Missing information can be restored well in this region, especially in HR videos, where the high-frequency content mostly consists of texture details.
Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topology
To the best of our knowledge, this work is the first principled approach toward adaptively combining global and local information under the context of RI point cloud analysis.
