Search Results for author: Hesheng Wang

Found 29 papers, 13 papers with code

3D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motion

no code implementations27 Sep 2022 Chaokang Jiang, Guangming Wang, Yanzi Miao, Hesheng Wang

The proposed method of self-supervised learning of 3D scene flow on real-world images is compared with a variety of methods for learning on the synthesized dataset and learning on LiDAR point clouds.

Optical Flow Estimation Scene Flow Estimation +1

FFPA-Net: Efficient Feature Fusion with Projection Awareness for 3D Object Detection

no code implementations15 Sep 2022 Chaokang Jiang, Guangming Wang, Jinxing Wu, Yanzi Miao, Hesheng Wang

Promising complementarity exists between the texture features of color images and the geometric information of LiDAR point clouds.

3D Object Detection object-detection

Unsupervised Learning of 3D Scene Flow with 3D Odometry Assistance

no code implementations11 Sep 2022 Guangming Wang, Zhiheng Feng, Chaokang Jiang, Hesheng Wang

Unlike the previous unsupervised learning of scene flow in point clouds, we propose to use odometry information to assist the unsupervised learning of scene flow and use real-world LiDAR data to train our network.

Activity Recognition Autonomous Driving +1

Pseudo-LiDAR for Visual Odometry

no code implementations4 Sep 2022 Huiying Deng, Guangming Wang, Zhiheng Feng, Chaokang Jiang, Xinrui Wu, Yanzi Miao, Hesheng Wang

In order to make full use of the rich point cloud information provided by the pseudo-LiDAR, a projection-aware dense odometry pipeline is adopted.

Stereo Matching Visual Odometry

What Matters for 3D Scene Flow Network

1 code implementation19 Jul 2022 Guangming Wang, Yunzhe Hu, Zhe Liu, Yiyang Zhou, Masayoshi Tomizuka, Wei Zhan, Hesheng Wang

Our proposed model surpasses all existing methods by at least 38. 2% on FlyingThings3D dataset and 24. 7% on KITTI Scene Flow dataset for EPE3D metric.

Scene Flow Estimation

Unsupervised Learning of 3D Scene Flow from Monocular Camera

1 code implementation8 Jun 2022 Guangming Wang, Xiaoyu Tian, Ruiqi Ding, Hesheng Wang

Unsupervised learning of scene flow in this paper mainly consists of two parts: (i) depth estimation and camera pose estimation, and (ii) scene flow estimation based on four different loss functions.

Depth Estimation Optical Flow Estimation +2

Interactive Multi-scale Fusion of 2D and 3D Features for Multi-object Tracking

no code implementations30 Mar 2022 Guangming Wang, Chensheng Peng, Jinpeng Zhang, Hesheng Wang

Specifically, through multi-scale interactive query and fusion between pixel-level and point-level features, our method, can obtain more distinguishing features to improve the performance of multiple object tracking.

Autonomous Driving Multi-Object Tracking +1

Efficient 3D Deep LiDAR Odometry

1 code implementation3 Nov 2021 Guangming Wang, Xinrui Wu, Shuyang Jiang, Zhe Liu, Hesheng Wang

An efficient 3D point cloud learning architecture, named EfficientLO-Net, for LiDAR odometry is first proposed in this paper.

Pose Estimation

Residual 3D Scene Flow Learning with Context-Aware Feature Extraction

no code implementations10 Sep 2021 Guangming Wang, Yunzhe Hu, Xinrui Wu, Hesheng Wang

To solve the first problem, a novel context-aware set convolution layer is proposed in this paper to exploit contextual structure information of Euclidean space and learn soft aggregation weights for local point features.

Autonomous Driving Scene Flow Estimation +1

NccFlow: Unsupervised Learning of Optical Flow With Non-occlusion from Geometry

no code implementations8 Jul 2021 Guangming Wang, Shuaiqi Ren, Hesheng Wang

Then, two novel loss functions are proposed for the unsupervised learning of optical flow based on the geometric laws of non-occlusion.

Autonomous Driving Optical Flow Estimation

Motion Projection Consistency Based 3D Human Pose Estimation with Virtual Bones from Monocular Videos

no code implementations28 Jun 2021 Guangming Wang, Honghao Zeng, Ziliang Wang, Zhe Liu, Hesheng Wang

Ablation studies demonstrate the effectiveness of the proposed inter-frame projection consistency constraints and intra-frame loop constraints.

3D Human Pose Estimation

Unsupervised Learning of Monocular Depth and Ego-Motion Using Multiple Masks

1 code implementation1 Apr 2021 Guangming Wang, Hesheng Wang, Yiling Liu, Weidong Chen

A new unsupervised learning method of depth and ego-motion using multiple masks from monocular video is proposed in this paper.

Depth Estimation Motion Estimation

A Registration-aided Domain Adaptation Network for 3D Point Cloud Based Place Recognition

1 code implementation9 Dec 2020 Zhijian Qiao, Hanjiang Hu, Weiang Shi, Siyuan Chen, Zhe Liu, Hesheng Wang

In the field of large-scale SLAM for autonomous driving and mobile robotics, 3D point cloud based place recognition has aroused significant research interest due to its robustness to changing environments with drastic daytime and weather variance.

Autonomous Driving Domain Adaptation +1

PWCLO-Net: Deep LiDAR Odometry in 3D Point Clouds Using Hierarchical Embedding Mask Optimization

1 code implementation CVPR 2021 Guangming Wang, Xinrui Wu, Zhe Liu, Hesheng Wang

A novel 3D point cloud learning model for deep LiDAR odometry, named PWCLO-Net, using hierarchical embedding mask optimization is proposed in this paper.

Pose Estimation

End-to-End 3D Point Cloud Learning for Registration Task Using Virtual Correspondences

1 code implementation30 Nov 2020 Zhijian Qiao, Huanshu Wei, Zhe Liu, Chuanzhe Suo, Hesheng Wang

3D Point cloud registration is still a very challenging topic due to the difficulty in finding the rigid transformation between two point clouds with partial correspondences, and it's even harder in the absence of any initial estimation information.

Point Cloud Registration

Spherical Interpolated Convolutional Network with Distance-Feature Density for 3D Semantic Segmentation of Point Clouds

no code implementations27 Nov 2020 Guangming Wang, Yehui Yang, Huixin Zhang, Zhe Liu, Hesheng Wang

In this paper, a spherical interpolated convolution operator is proposed to replace the traditional grid-shaped 3D convolution operator.

3D Semantic Segmentation

Learning of Long-Horizon Sparse-Reward Robotic Manipulator Tasks with Base Controllers

no code implementations24 Nov 2020 Guangming Wang, Minjian Xin, Wenhua Wu, Zhe Liu, Hesheng Wang

Deep Reinforcement Learning (DRL) enables robots to perform some intelligent tasks end-to-end.

SeasonDepth: Cross-Season Monocular Depth Prediction Dataset and Benchmark under Multiple Environments

1 code implementation9 Nov 2020 Hanjiang Hu, Baoquan Yang, Zhijian Qiao, Ding Zhao, Hesheng Wang

Different environments pose a great challenge on the outdoor robust visual perception for long-term autonomous driving and the generalization of learning-based algorithms on different environmental effects is still an open problem.

Autonomous Driving Depth Estimation +4

Hierarchical Attention Learning of Scene Flow in 3D Point Clouds

no code implementations12 Oct 2020 Guangming Wang, Xinrui Wu, Zhe Liu, Hesheng Wang

In this paper, a novel hierarchical neural network with double attention is proposed for learning the correlation of point features in adjacent frames and refining scene flow from coarse to fine layer by layer.

Autonomous Driving Optical Flow Estimation +1

DASGIL: Domain Adaptation for Semantic and Geometric-aware Image-based Localization

1 code implementation1 Oct 2020 Hanjiang Hu, Zhijian Qiao, Ming Cheng, Zhe Liu, Hesheng Wang

Long-Term visual localization under changing environments is a challenging problem in autonomous driving and mobile robotics due to season, illumination variance, etc.

Autonomous Driving Domain Adaptation +4

Unsupervised Learning of Depth, Optical Flow and Pose with Occlusion from 3D Geometry

1 code implementation arXiv 2020 Guangming Wang, Chi Zhang, Hesheng Wang, Jingchuan Wang, Yong Wang, Xinlei Wang

In the occluded region, as depth and camera motion can provide more reliable motion estimation, they can be used to instruct unsupervised learning of optical flow.

Autonomous Driving Depth And Camera Motion +3

Retrieval-based Localization Based on Domain-invariant Feature Learning under Changing Environments

1 code implementation23 Sep 2019 Hanjiang Hu, Hesheng Wang, Zhe Liu, Chenguang Yang, Weidong Chen, Le Xie

To retrieve a target image from the database, the query image is first encoded using the encoder belonging to the query domain to obtain a domain-invariant feature vector.

Autonomous Driving Translation +1

Learning Actions from Human Demonstration Video for Robotic Manipulation

no code implementations10 Sep 2019 Shuo Yang, Wei zhang, Weizhi Lu, Hesheng Wang, Yibin Li

However, the general video captioning methods focus more on the understanding of the full frame, lacking of consideration on the specific object of interests in robotic manipulations.

Video Captioning

LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis

2 code implementations ICCV 2019 Zhe Liu, Shunbo Zhou, Chuanzhe Suo, Yingtian Liu, Peng Yin, Hesheng Wang, Yun-hui Liu

Point cloud based place recognition is still an open issue due to the difficulty in extracting local features from the raw 3D point cloud and generating the global descriptor, and it's even harder in the large-scale dynamic environments.

Point Cloud Retrieval Visual Place Recognition

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