201 citations · 592 across the 23 of their papers we have counts for
23 papers
Learning 3D Reconstruction with Priors in Test Time
Lei Zhou, Haoyu Wu, Akshat Dave +1
We introduce a test-time framework for multiview Transformers (MVTs) that incorporates priors (e.g., camera poses, intrinsics, and depth) to improve 3D tasks without retraining or…
ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer
Hongkai Chen, Zixin Luo, Lei Zhou +6
Generating robust and reliable correspondences across images is a fundamental task for a diversity of applications. To capture context at both global and local granularity, we prop…
Learning to Match Features with Seeded Graph Matching Network
Hongkai Chen, Zixin Luo, Jiahui Zhang +5
Matching local features across images is a fundamental problem in computer vision. Targeting towards high accuracy and efficiency, we propose Seeded Graph Matching Network, a graph…
PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency
Xuyang Bai, Zixin Luo, Lei Zhou +5
Removing outlier correspondences is one of the critical steps for successful feature-based point cloud registration. Despite the increasing popularity of introducing deep learning…
Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation
Mingmin Zhen, Shiwei Li, Lei Zhou +4
In this paper, we introduce a novel network, called discriminative feature network (DFNet), to address the unsupervised video object segmentation task. To capture the inherent corr…
Stochastic Bundle Adjustment for Efficient and Scalable 3D Reconstruction
Lei Zhou, Zixin Luo, Mingmin Zhen +5
Current bundle adjustment solvers such as the Levenberg-Marquardt (LM) algorithm are limited by the bottleneck in solving the Reduced Camera System (RCS) whose dimension is proport…
Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency
Jiaxiang Shang, Tianwei Shen, Shiwei Li +4
Recent learning-based approaches, in which models are trained by single-view images have shown promising results for monocular 3D face reconstruction, but they suffer from the ill-…
End-to-end Optimized Video Compression with MV-Residual Prediction
XiangJi Wu, Ziwen Zhang, Jie Feng +2
We present an end-to-end trainable framework for P-frame compression in this paper. A joint motion vector (MV) and residual prediction network MV-Residual is designed to extract th…
ASLFeat: Learning Local Features of Accurate Shape and Localization
Zixin Luo, Lei Zhou, Xuyang Bai +6
This work focuses on mitigating two limitations in the joint learning of local feature detectors and descriptors. First, the ability to estimate the local shape (scale, orientation…
Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contexts
Mingmin Zhen, Jinglu Wang, Lei Zhou +5
In this paper, we present a joint multi-task learning framework for semantic segmentation and boundary detection. The critical component in the framework is the iterative pyramid c…
KFNet: Learning Temporal Camera Relocalization using Kalman Filtering
Lei Zhou, Zixin Luo, Tianwei Shen +5
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. Even though th…
D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
Xuyang Bai, Zixin Luo, Lei Zhou +3
A successful point cloud registration often lies on robust establishment of sparse matches through discriminative 3D local features. Despite the fast evolution of learning-based 3D…
BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks
Yao Yao, Zixin Luo, Shiwei Li +5
While deep learning has recently achieved great success on multi-view stereo (MVS), limited training data makes the trained model hard to be generalized to unseen scenarios. Compar…
Self-Supervised Learning of Depth and Motion Under Photometric Inconsistency
Tianwei Shen, Lei Zhou, Zixin Luo +5
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 les…
Learning Two-View Correspondences and Geometry Using Order-Aware Network
Jiahui Zhang, Dawei Sun, Zixin Luo +6
Establishing correspondences between two images requires both local and global spatial context. Given putative correspondences of feature points in two views, in this paper, we pro…
ContextDesc: Local Descriptor Augmentation with Cross-Modality Context
Zixin Luo, Tianwei Shen, Lei Zhou +5
Most existing studies on learning local features focus on the patch-based descriptions of individual keypoints, whereas neglecting the spatial relations established from their keyp…
Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation
Tianwei Shen, Zixin Luo, Lei Zhou +4
Accurate relative pose is one of the key components in visual odometry (VO) and simultaneous localization and mapping (SLAM). Recently, the self-supervised learning framework that…
Matchable Image Retrieval by Learning from Surface Reconstruction
Tianwei Shen, Zixin Luo, Lei Zhou +4
Convolutional Neural Networks (CNNs) have achieved superior performance on object image retrieval, while Bag-of-Words (BoW) models with handcrafted local features still dominate th…
End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion
Chao Shang, Yun Tang, Jing Huang +3
Knowledge graph embedding has been an active research topic for knowledge base completion, with progressive improvement from the initial TransE, TransH, DistMult et al to the curre…
GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints
Zixin Luo, Tianwei Shen, Lei Zhou +5
Learned local descriptors based on Convolutional Neural Networks (CNNs) have achieved significant improvements on patch-based benchmarks, whereas not having demonstrated strong gen…
Learning and Matching Multi-View Descriptors for Registration of Point Clouds
Lei Zhou, Siyu Zhu, Zixin Luo +5
Critical to the registration of point clouds is the establishment of a set of accurate correspondences between points in 3D space. The correspondence problem is generally addressed…
Face Parsing via a Fully-Convolutional Continuous CRF Neural Network
Lei Zhou, Zhi Liu, Xiangjian He
In this work, we address the face parsing task with a Fully-Convolutional continuous CRF Neural Network (FC-CNN) architecture. In contrast to previous face parsing methods that app…
Parallel Structure from Motion from Local Increment to Global Averaging
Siyu Zhu, Tianwei Shen, Lei Zhou +4
In this paper, we tackle the accurate and consistent Structure from Motion (SfM) problem, in particular camera registration, far exceeding the memory of a single computer in parall…