Y
Yulan Guo
Researcher at National University of Defense Technology
Publications - 196
Citations - 9683
Yulan Guo is an academic researcher from National University of Defense Technology. The author has contributed to research in topics: Computer science & Point cloud. The author has an hindex of 30, co-authored 164 publications receiving 5012 citations. Previous affiliations of Yulan Guo include Chinese Academy of Sciences & University of Western Australia.
Papers
More filters
Journal ArticleDOI
Selective Light Field Refocusing for Camera Arrays Using Bokeh Rendering and Superresolution
TL;DR: In this paper, a light field refocusing method was proposed to improve the imaging quality of camera arrays by estimating the disparity of the disparity and then rendering the focused region (bokeh) by using a depth-based anisotropic filter.
Journal ArticleDOI
Local-to-Global Cost Aggregation for Semantic Correspondence
TL;DR: CACT as discussed by the authors proposes a cost aggregation network with convolutions and transformers, which refines the correlation map in a local-to-global manner by utilizing the strengths of convolutional and transformer in different stages.
Posted Content
Spatial-Temporal Transformer for 3D Point Cloud Sequences
TL;DR: Point Spatial-Temporal Transformer (PST2) as mentioned in this paper is proposed to learn spatial-temporal representations from dynamic 3D point cloud sequences, which consists of two major modules: a Spatio-Temoral Self-Attention (STSA) module and a Resolution Embedding (RE) module.
Supplementary Material – 3DAC: Learning Attribute Compression for Point Clouds
TL;DR: This document describes details of Region Adaptive Hierarchical Transform (RAHT) and then describes network architecture details of the algorithm, and shows additional qualitative results on ScanNet and SemanticKITTI.
Journal ArticleDOI
Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting
TL;DR: Zhang et al. as mentioned in this paper proposed to use a neural network to estimate the overlap between scan pairs, which enables them to construct a sparse but reliable pose graph, and designed a novel history reweighting function in the IRLS scheme, which has strong robustness to outlier edges on the graph.