Search Results for author: Chiew-Lan Tai

Found 7 papers, 4 papers with code

D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features

2 code implementations CVPR 2020 Xuyang Bai, Zixin Luo, Lei Zhou, Hongbo Fu, Long Quan, Chiew-Lan Tai

In this paper, we leverage a 3D fully convolutional network for 3D point clouds, and propose a novel and practical learning mechanism that densely predicts both a detection score and a description feature for each 3D point.

Point Cloud Registration

SketchDesc: Learning Local Sketch Descriptors for Multi-view Correspondence

no code implementations16 Jan 2020 Deng Yu, Lei LI, Youyi Zheng, Manfred Lau, Yi-Zhe Song, Chiew-Lan Tai, Hongbo Fu

In this paper, we study the problem of multi-view sketch correspondence, where we take as input multiple freehand sketches with different views of the same object and predict as output the semantic correspondence among the sketches.

Semantic correspondence

Sketch-R2CNN: An Attentive Network for Vector Sketch Recognition

no code implementations20 Nov 2018 Lei Li, Changqing Zou, Youyi Zheng, Qingkun Su, Hongbo Fu, Chiew-Lan Tai

To bridge the gap between these two spaces in neural networks, we propose a neural line rasterization module to convert the vector sketch along with the attention estimated by RNN into a bitmap image, which is subsequently consumed by CNN.

Sketch Recognition

Higher-Order CRF Structural Segmentation of 3D Reconstructed Surfaces

no code implementations ICCV 2015 Jingbo Liu, Jinglu Wang, Tian Fang, Chiew-Lan Tai, Long Quan

In this paper, we propose a structural segmentation algorithm to partition multi-view stereo reconstructed surfaces of large-scale urban environments into structural segments.

Cannot find the paper you are looking for? You can Submit a new open access paper.