Search Results for author: Lingjing Wang

Found 17 papers, 3 papers with code

Learn to Learn Metric Space for Few-Shot Segmentation of 3D Shapes

no code implementations7 Jul 2021 Xiang Li, Lingjing Wang, Yi Fang

To achieve this, we treat the shape segmentation as a point labeling problem in the metric space.


3D Meta-Registration: Learning to Learn Registration of 3D Point Clouds

no code implementations22 Oct 2020 Lingjing Wang, Yu Hao, Xiang Li, Yi Fang

In this paper, we propose a meta-learning based 3D registration model, named 3D Meta-Registration, that is capable of rapidly adapting and well generalizing to new 3D registration tasks for unseen 3D point clouds.

Meta-Learning Point Cloud Registration

3D Meta Point Signature: Learning to Learn 3D Point Signature for 3D Dense Shape Correspondence

no code implementations21 Oct 2020 Hao Huang, Lingjing Wang, Xiang Li, Yi Fang

In this paper, we propose a novel meta-learning based 3D point signature model, named 3Dmetapointsignature (MEPS) network, that is capable of learning robust point signatures in 3D shapes.

3D Dense Shape Correspondence Meta-Learning

Deep-3DAligner: Unsupervised 3D Point Set Registration Network With Optimizable Latent Vector

no code implementations29 Sep 2020 Lingjing Wang, Xiang Li, Yi Fang

Point cloud registration is the process of aligning a pair of point sets via searching for a geometric transformation.

Point Cloud Registration

Unsupervised Partial Point Set Registration via Joint Shape Completion and Registration

no code implementations11 Sep 2020 Xiang Li, Lingjing Wang, Yi Fang

To bridge the performance gaps between partial point set registration with full point set registration, we proposed to incorporate a shape completion network to benefit the registration process.

Robust Image Matching By Dynamic Feature Selection

no code implementations13 Aug 2020 Hao Huang, Jianchun Chen, Xiang Li, Lingjing Wang, Yi Fang

Recent works introduce convolutional neural networks (CNNs) to extract high-level feature maps and find correspondences through feature matching.

Decision Making

GP-Aligner: Unsupervised Non-rigid Groupwise Point Set Registration Based On Optimized Group Latent Descriptor

no code implementations25 Jul 2020 Lingjing Wang, Xiang Li, Yi Fang

More specifically, for a given group we first define an optimizable Group Latent Descriptor (GLD) to characterize the gruopwise relationship among a group of point sets.

Unsupervised Learning of Global Registration of Temporal Sequence of Point Clouds

no code implementations17 Jun 2020 Lingjing Wang, Yi Shi, Xiang Li, Yi Fang

Global registration of point clouds aims to find an optimal alignment of a sequence of 2D or 3D point sets.

Unsupervised Learning of 3D Point Set Registration

no code implementations11 Jun 2020 Lingjing Wang, Xiang Li, Yi Fang

Moreover, for a pair of source and target point sets, existing deep learning mechanisms require explicitly designed encoders to extract both deep spatial features from unstructured point clouds and their spatial correlation representation, which is further fed to a decoder to regress the desired geometric transformation for point set alignment.

Point Cloud Registration

Geometry-Aware Segmentation of Remote Sensing Images via Implicit Height Estimation

no code implementations10 Jun 2020 Xiang Li, Lingjing Wang, Yi Fang

Recent studies have shown the benefits of using additional elevation data (e. g., DSM) for enhancing the performance of the semantic segmentation of aerial images.

Semantic Segmentation

Arbicon-Net: Arbitrary Continuous Geometric Transformation Networks for Image Registration

1 code implementation NeurIPS 2019 Jianchun Chen, Lingjing Wang, Xiang Li, Yi Fang

To address this issue, we present an end-to-end trainable deep neural networks, named Arbitrary Continuous Geometric Transformation Networks (Arbicon-Net), to directly predict the dense displacement field for pairwise image alignment.

Image Registration

Residual Switching Network for Portfolio Optimization

no code implementations16 Oct 2019 Jifei Wang, Lingjing Wang

This paper studies deep learning methodologies for portfolio optimization in the US equities market.

Portfolio Optimization

Density-Aware Convolutional Networks with Context Encoding for Airborne LiDAR Point Cloud Classification

no code implementations14 Oct 2019 Xiang Li, Mingyang Wang, Congcong Wen, Lingjing Wang, Nan Zhou, Yi Fang

Based on this convolution module, we further developed a multi-scale fully convolutional neural network with downsampling and upsampling blocks to enable hierarchical point feature learning.

3D Point Cloud Classification General Classification +1

Coherent Point Drift Networks: Unsupervised Learning of Non-Rigid Point Set Registration

3 code implementations7 Jun 2019 Lingjing Wang, Xiang Li, Jianchun Chen, Yi Fang

In contrast to previous efforts (e. g. coherent point drift), CPD-Net can learn displacement field function to estimate geometric transformation from a training dataset, consequently, to predict the desired geometric transformation for the alignment of previously unseen pairs without any additional iterative optimization process.

Non-Rigid Point Set Registration Networks

1 code implementation2 Apr 2019 Lingjing Wang, Jianchun Chen, Xiang Li, Yi Fang

In contrast, the proposed point registration neural network (PR-Net) actively learns the registration pattern as a parametric function from a training dataset, consequently predict the desired geometric transformation to align a pair of point sets.

Unsupervised 3D Reconstruction from a Single Image via Adversarial Learning

no code implementations26 Nov 2017 Lingjing Wang, Yi Fang

Recent advancements in deep learning opened new opportunities for learning a high-quality 3D model from a single 2D image given sufficient training on large-scale data sets.

3D Reconstruction

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