2 citations · 2 across the 7 of their papers we have counts for
7 papers
Fast and Interpretable 2D Homography Decomposition: Similarity-Kernel-Similarity and Affine-Core-Affine Transformations
Shen Cai, Zhanhao Wu, Lingxi Guo +4
In this paper, we present two fast and interpretable decomposition methods for 2D homography, which are named Similarity-Kernel-Similarity (SKS) and Affine-Core-Affine (ACA) transf…
An Efficient End-to-End 3D Voxel Reconstruction based on Neural Architecture Search
Yongdong Huang, Yuanzhan Li, Xulong Cao +5
Using neural networks to represent 3D objects has become popular. However, many previous works employ neural networks with fixed architecture and size to represent different 3D obj…
High-fidelity 3D Model Compression based on Key Spheres
Yuanzhan Li, Yuqi Liu, Yujie Lu +3
In recent years, neural signed distance function (SDF) has become one of the most effective representation methods for 3D models. By learning continuous SDFs in 3D space, neural ne…
SN-Graph: a Minimalist 3D Object Representation for Classification
Siyu Zhang, Hui Cao, Yuqi Liu +4
Using deep learning techniques to process 3D objects has achieved many successes. However, few methods focus on the representation of 3D objects, which could be more effective for…
Spherical Transformer: Adapting Spherical Signal to CNNs
Yuqi Liu, Yin Wang, Haikuan Du +1
Convolutional neural networks (CNNs) have been widely used in various vision tasks, e.g. image classification, semantic segmentation, etc. Unfortunately, standard 2D CNNs are not w…
A Fast Hybrid Cascade Network for Voxel-based 3D Object Classification
Ji Luo, Hui Cao, Jie Wang +2
Voxel-based 3D object classification has been thoroughly studied in recent years. Most previous methods convert the classic 2D convolution into a 3D form that will be further appli…
InSphereNet: a Concise Representation and Classification Method for 3D Object
Hui Cao, Haikuan Du, Siyu Zhang +1
In this paper, we present an InSphereNet method for the problem of 3D object classification. Unlike previous methods that use points, voxels, or multi-view images as inputs of deep…