Chengyu Qiao

Dr. Chengyu Qiao

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 March 2023 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
JFJingyun Fu
Jingyun Fu
ZXZhiyu Xiang
Zhiyu Xiang
CQChengyu Qiao
Chengyu Qiao
TBTingming Bai
Tingming Bai
As a low-level task of 3D perception, scene flow is a fundamental representation of dynamic scenes and provides non-rigid motion descriptions for the objects in the 3D environment, which can strongly support many upper-level applications. Inspired by the revolutionary success of deep learning, many attention-based neural networks have recently been proposed to estimate scene flow from consecutive point clouds. However, extracting effective features and estimating accurate point motions for irregular and occluded point clouds remains a challenging task. In this letter, we propose PT-FlowNet, the first end-to-end scene flow estimation network embedding the point transformer (PT) into all functional stages of the task. In particular, we design novel PT-based modules for point feature extraction, iterative flow update, and flow refinement stage to encourage effective point-level feature aggregation. Experimental results on FlyingThings3D and KITTI datasets show that our PT-FlowNet achieves state-of-the-art performance. Trained on synthetic data only, our PT-FlowNet can generalize to real-world scans and outperforms the existing methods by at least 36.2% for the EPE3D metric on the KITTI dataset.

16 August 2019 in IEEE Access
Verified
Journal Article
Open access
NZNan Zou
Nan Zou
ZXZhiyu Xiang
Zhiyu Xiang
Yiman ChenYiman Chen
Yiman Chen
SCShuya Chen
Shuya Chen
CQChengyu Qiao
Chengyu Qiao
Semantic segmentation has always been a fundamental and critical task to scene understanding. Current deep convolutional neural networks (DCNN) are able to successfully learn context from very large receptive fields due to convolutions with deep layers. However, current convolutions in DCNNs does not consider local object boundaries that are the borders among different semantic regions. Convolution with equal contribution on the pixels across the boundary may lead to inferior segmentation results. In this paper, a novel boundary-aware convolution is proposed. It is able to effectively fuse features by adaptively assigning contributions from pixels within receptive fields according to the boundary similarity map. A new semantic segmentation network based on classical FCN8S is then designed by employing multi-scale boundary-aware convolution. The whole network is implemented end-to-end and evaluated with heterogeneous RGB and depth input. Experiments conducted on multiple datasets show that our boundary-aware CNN can effectively improve the semantic segmentation performance.

23 January 2020 in Sensors
Verified
Journal Article
Open access
PDF file
NZNan Zou
Nan Zou
ZXZhiyu Xiang
Zhiyu Xiang
Yiman ChenYiman Chen
Yiman Chen
SCShuya Chen
Shuya Chen
CQChengyu Qiao
Chengyu Qiao
As the core task of scene understanding, semantic segmentation and depth completion play a vital role in lots of applications such as robot navigation, AR/VR and autonomous driving. They are responsible for parsing scenes from the angle of semantics and geometry, respectively. While great progress has been made in both tasks through deep learning technologies, few works have been done on building a joint model by deeply exploring the inner relationship of the above tasks. In this paper, semantic segmentation and depth completion are jointly considered under a multi-task learning framework. By sharing a common encoder part and introducing boundary features as inner constraints in the decoder part, the two tasks can properly share the required information from each other. An extra boundary detection sub-task is responsible for providing the boundary features and constructing cross-task joint loss functions for network training. The entire network is implemented end-to-end and evaluated with both RGB and sparse depth input. Experiments conducted on synthesized and real scene datasets show that our proposed multi-task CNN model can effectively improve the performance of every single task.

14 June 2023 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
CQChengyu Qiao
Chengyu Qiao
ZXZhiyu Xiang
Zhiyu Xiang
YFYuangang Fan
Yuangang Fan
TBTingming Bai
Tingming Bai
XZXijun ZHAO
Xijun ZHAO
JFJingyun Fu
Jingyun Fu
Visual relocalization aims to estimate the absolute camera pose from an image or sequential images. Recent works tackle this problem by exploiting deep neural networks to regress camera poses. However, spatial and temporal clues from sequential images still remain underexplored, resulting in inaccurate poses and large outliers. In this letter, we introduce a novel vision Transformer based absolute pose regression model, TransAPR, to tackle this problem. Upon the traditional CNN backbone, we design Transformer based spatial and temporal fusion modules respectively to realize sufficient feature interaction among the neighboring images in the sequence. A hierarchical feature aggregation (HFA) module is further designed to aggregate multi-scale and multi-level features in the pose regressor. Benefiting from these delicate designs, our model is able to generate reliable image representations for absolute pose regression, resulting in more robust localization under challenging environments. We conduct extensive experiments on various indoor and outdoor datasets and show that our method achieves state-of-the-art performance.

27 February 2021
Verified
Book Chapter
Closed access
PDF file
SCShuya Chen
Shuya Chen
ZXZhiyu Xiang
Zhiyu Xiang
CQChengyu Qiao
Chengyu Qiao
Yiman ChenYiman Chen
Yiman Chen
TBTingming Bai
Tingming Bai

21 October 2019 in Measurement Science and Technology
Verified
Journal Article
Closed access
SCShuya Chen
Shuya Chen
ZXZhiyu Xiang
Zhiyu Xiang
NZNan Zou
Nan Zou
Yiman ChenYiman Chen
Yiman Chen
CQChengyu Qiao
Chengyu Qiao
Omnidirectional catadioptric systems are popular in many fields, such as robotics, surveillance, telepresence and virtual reality, thanks to their large field of view. For 3D scene reconstruction in a single shot, usually two different catadioptric cameras are needed. More cameras may contribute to better reconstruction while a larger mounting space and higher power cost are required. In this paper, a single camera multi-mirror catadioptric system with a vertical and horizontal baseline structure is proposed. It features the realization of multiple central or non-central omnidirectional stereo pairs in a compact manner. To make the 3D reconstruction process general and adaptive to various types of system configurations, a flexible calibration and reconstruction algorithm pipeline is presented. The algorithm features the approximation of the system into multiple central sub-cameras and carries out stereo matching in a spherical representation. In addition, an effective 3D point cloud fusion algorithm is proposed to optimize the reconstruction results from multiple stereo pairs. Experiments carried out with synthetic and real data verified the feasibility and effectiveness of our system. In particular, with the real data, when compared with the results of a single stereo pair, the fused reconstruction results of the multiple stereo pairs obtained 30% and 15% improvement corresponding to the planarity and angle error respectively.