Search Results for author: Zixin Luo

Found 19 papers, 18 papers with code

ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer

1 code implementation30 Aug 2022 Hongkai Chen, Zixin Luo, Lei Zhou, Yurun Tian, Mingmin Zhen, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan

Generating robust and reliable correspondences across images is a fundamental task for a diversity of applications.

Homography Estimation

Learning to Match Features with Seeded Graph Matching Network

1 code implementation ICCV 2021 Hongkai Chen, Zixin Luo, Jiahui Zhang, Lei Zhou, Xuyang Bai, Zeyu Hu, Chiew-Lan Tai, Long Quan

2) Seeded Graph Neural Network, which utilizes seed matches to pass messages within/across images and predicts assignment costs.

Graph Matching

Visibility-aware Multi-view Stereo Network

1 code implementation18 Aug 2020 Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang

As such, the adverse influence of occluded pixels is suppressed in the cost fusion.

3D Reconstruction Depth Estimation +1

Learning Stereo Matchability in Disparity Regression Networks

1 code implementation11 Aug 2020 Jingyang Zhang, Yao Yao, Zixin Luo, Shiwei Li, Tianwei Shen, Tian Fang, Long Quan

Finally, a matchability-aware disparity refinement is introduced to improve the depth inference in weakly matchable regions.

regression Stereo Disparity Estimation +1

Stochastic Bundle Adjustment for Efficient and Scalable 3D Reconstruction

1 code implementation ECCV 2020 Lei Zhou, Zixin Luo, Mingmin Zhen, Tianwei Shen, Shiwei Li, Zhuofei Huang, Tian Fang, Long Quan

In this work, we propose a stochastic bundle adjustment algorithm which seeks to decompose the RCS approximately inside the LM iterations to improve the efficiency and scalability.

3D Reconstruction Clustering

KFNet: Learning Temporal Camera Relocalization using Kalman Filtering

1 code implementation CVPR 2020 Lei Zhou, Zixin Luo, Tianwei Shen, Jiahui Zhang, Mingmin Zhen, Yao Yao, Tian Fang, Long Quan

Temporal camera relocalization estimates the pose with respect to each video frame in sequence, as opposed to one-shot relocalization which focuses on a still image.

Camera Relocalization

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

BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks

2 code implementations CVPR 2020 Yao Yao, Zixin Luo, Shiwei Li, Jingyang Zhang, Yufan Ren, Lei Zhou, Tian Fang, Long Quan

Compared with other computer vision tasks, it is rather difficult to collect a large-scale MVS dataset as it requires expensive active scanners and labor-intensive process to obtain ground truth 3D structures.

3D Reconstruction

Self-Supervised Learning of Depth and Motion Under Photometric Inconsistency

1 code implementation19 Sep 2019 Tianwei Shen, Lei Zhou, Zixin Luo, Yao Yao, Shiwei Li, Jiahui Zhang, Tian Fang, Long Quan

The self-supervised learning of depth and pose from monocular sequences provides an attractive solution by using the photometric consistency of nearby frames as it depends much less on the ground-truth data.

Pose Estimation Self-Supervised Learning

Learning Two-View Correspondences and Geometry Using Order-Aware Network

1 code implementation ICCV 2019 Jiahui Zhang, Dawei Sun, Zixin Luo, Anbang Yao, Lei Zhou, Tianwei Shen, Yurong Chen, Long Quan, Hongen Liao

First, to capture the local context of sparse correspondences, the network clusters unordered input correspondences by learning a soft assignment matrix.

Vocal Bursts Valence Prediction

ContextDesc: Local Descriptor Augmentation with Cross-Modality Context

1 code implementation CVPR 2019 Zixin Luo, Tianwei Shen, Lei Zhou, Jiahui Zhang, Yao Yao, Shiwei Li, Tian Fang, Long Quan

Most existing studies on learning local features focus on the patch-based descriptions of individual keypoints, whereas neglecting the spatial relations established from their keypoint locations.

Geometric Matching

Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference

1 code implementation CVPR 2019 Yao Yao, Zixin Luo, Shiwei Li, Tianwei Shen, Tian Fang, Long Quan

However, one major limitation of current learned MVS approaches is the scalability: the memory-consuming cost volume regularization makes the learned MVS hard to be applied to high-resolution scenes.

Vocal Bursts Intensity Prediction

Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation

1 code implementation25 Feb 2019 Tianwei Shen, Zixin Luo, Lei Zhou, Hanyu Deng, Runze Zhang, Tian Fang, Long Quan

Accurate relative pose is one of the key components in visual odometry (VO) and simultaneous localization and mapping (SLAM).

Motion Estimation Self-Supervised Learning +2

Matchable Image Retrieval by Learning from Surface Reconstruction

1 code implementation26 Nov 2018 Tianwei Shen, Zixin Luo, Lei Zhou, Runze Zhang, Siyu Zhu, Tian Fang, Long Quan

Convolutional Neural Networks (CNNs) have achieved superior performance on object image retrieval, while Bag-of-Words (BoW) models with handcrafted local features still dominate the retrieval of overlapping images in 3D reconstruction.

3D Reconstruction Image Retrieval +2

GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints

1 code implementation ECCV 2018 Zixin Luo, Tianwei Shen, Lei Zhou, Siyu Zhu, Runze Zhang, Yao Yao, Tian Fang, Long Quan

Learned local descriptors based on Convolutional Neural Networks (CNNs) have achieved significant improvements on patch-based benchmarks, whereas not having demonstrated strong generalization ability on recent benchmarks of image-based 3D reconstruction.

3D Reconstruction

Learning and Matching Multi-View Descriptors for Registration of Point Clouds

no code implementations ECCV 2018 Lei Zhou, Siyu Zhu, Zixin Luo, Tianwei Shen, Runze Zhang, Mingmin Zhen, Tian Fang, Long Quan

Critical to the registration of point clouds is the establishment of a set of accurate correspondences between points in 3D space.

MVSNet: Depth Inference for Unstructured Multi-view Stereo

4 code implementations ECCV 2018 Yao Yao, Zixin Luo, Shiwei Li, Tian Fang, Long Quan

We present an end-to-end deep learning architecture for depth map inference from multi-view images.

Ranked #19 on Point Clouds on Tanks and Temples (Mean F1 (Intermediate) metric)

3D Reconstruction Point Clouds

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