Zheng Qin

Zheng Qin

Auto-generated profile, based on publicly available information

Zheng Qin

Defense Innovation Institute, Academy of Military Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

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

Representative Publications

View All Publications
20 March 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
ZQZheng Qin
Zheng Qin
HYHao Yu
Hao Yu
CWChangjian Wang
Changjian Wang
YGYulan Guo
Yulan Guo
YPYuxing Peng
Yuxing Peng
Kai XuKai Xu
Kai Xu
We study the problem of extracting accurate correspondences for point cloud registration. Recent keypoint-free methods have shown great potential through bypassing the detection of repeatable keypoints which is difficult to do especially in low-overlap scenarios. They seek correspondences over downsampled superpoints, which are then propagated to dense points. Superpoints are matched based on whether their neighboring patches overlap. Such sparse and loose matching requires contextual features capturing the geometric structure of the point clouds. We propose Geometric Transformer, or GeoTransformer for short, to learn geometric feature for robust superpoint matching. It encodes pair-wise distances and triplet-wise angles, making it invariant to rigid transformation and robust in low-overlap cases. The simplistic design attains surprisingly high matching accuracy such that no RANSAC is required in the estimation of alignment transformation, leading to 100 times acceleration. Extensive experiments on rich benchmarks encompassing indoor, outdoor, synthetic, multiway and non-rigid demonstrate the efficacy of GeoTransformer. Notably, our method improves the inlier ratio by $18{\sim }31$ percentage points and the registration recall by over 7 points on the challenging 3DLoMatch benchmark.

3 January 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
HYHao Yu
Hao Yu
JHJi Hou
Ji Hou
ZQZheng Qin
Zheng Qin
MSMahdi Saleh
Mahdi Saleh
ISIvan Shugurov
Ivan Shugurov
SISlobodan Ilic
Slobodan Ilic
Successful point cloud registration relies on accurate correspondences established upon powerful descriptors. However, existing neural descriptors either leverage a rotation-variant backbone whose performance declines under large rotations, or encode local geometry that is less distinctive. To address this issue, we introduce RIGA to learn descriptors that are Rotation-Invariant by design and Globally-Aware. From the Point Pair Features (PPFs) of sparse local regions, rotation-invariant local geometry is encoded into geometric descriptors. Global awareness of 3D structures and geometric context is subsequently incorporated, both in a rotation-invariant fashion. More specifically, 3D structures of the whole frame are first represented by our global PPF signatures, from which structural descriptors are learned to help geometric descriptors sense the 3D world beyond local regions. Geometric context from the whole scene is then globally aggregated into descriptors. Finally, the description of sparse regions is interpolated to dense point descriptors, from which correspondences are extracted for registration. To validate our approach, we conduct extensive experiments on both object- and scene-level data. With large rotations, RIGA surpasses the state-of-the-art methods by a margin of 8 ${}^\circ$ in terms of the Relative Rotation Error on ModelNet40 and improves the Feature Matching Recall by at least 5 percentage points on 3DLoMatch.

1 April 2024 in Computational Visual Media
Verified
Journal Article
Open access
PDF file
ZGZhirui Gao
Zhirui Gao
RYRenjiao Yi
Renjiao Yi
ZQZheng Qin
Zheng Qin
YYYunfan Ye
Yunfan Ye
CZChenyang Zhu
Chenyang Zhu
Kai XuKai Xu
Kai Xu
Template matching is a fundamental task in computer vision and has been studied for decades. It plays an essential role in manufacturing industry for estimating the poses of different parts, facilitating downstream tasks such as robotic grasping. Existing methods fail when the template and source images have different modalities, cluttered backgrounds, or weak textures. They also rarely consider geometric transformations via homographies, which commonly exist even for planar industrial parts. To tackle the challenges, we propose an accurate template matching method based on differentiable coarse-to-fine correspondence refinement. We use an edge-aware module to overcome the domain gap between the mask template and the grayscale image, allowing robust matching. An initial warp is estimated using coarse correspondences based on novel structure-aware information provided by transformers. This initial alignment is passed to a refinement network using references and aligned images to obtain sub-pixel level correspondences which are used to give the final geometric transformation. Extensive evaluation shows that our method to be significantly better than state-of-the-art methods and baselines, providing good generalization ability and visually plausible results even on unseen real data.

1 January 2018 in IEEE Access
Verified
Journal Article
Open access
ZQZheng Qin
Zheng Qin
ZZZhaoning Zhang
Zhaoning Zhang
SZShiqing Zhang
Shiqing Zhang
HYHao Yu
Hao Yu
YPYuxing Peng
Yuxing Peng
Compact neural networks are inclined to exploit “sparsely-connected” convolutions such as depthwise convolution and group convolution for employment in mobile applications. Compared with standard “fully-connected” convolutions, these convolutions are more computationally economical. However, “sparsely-connected” convolutions block the inter-group information exchange, which induces severe performance degradation. To address this issue, we present two novel operations named merging and evolution to leverage the inter-group information. Our key idea is encoding the inter-group information with a narrow feature map, then combining the generated features with the original network for better representation. Taking advantage of the proposed operations, we then introduce the Merging-and-Evolution (ME) module, an architectural unit specifically designed for compact networks. Finally, we propose a family of compact neural networks called MENet based on the ME modules. Extensive experiments on CIFAR, SVHN, ILSVRC 2012, and PASCAL VOC 2007 datasets demonstrate that MENet consistently outperforms other state-of-the-art compact networks under different computational budgets. For instance, under the computational budget of 140 MFLOPs, MENet surpasses ShuffleNet by 1% and MobileNet by 1.95% on ILSVRC 2012 top-1 accuracy, while by 2.9% and 4.1% on PASCAL VOC 2007 mAP, respectively.

31 March 2005
Verified
Conference Paper
Closed access
BFBao Fumin
Bao Fumin
LALi Aiguo
Li Aiguo
QZQin Zheng
Qin Zheng

19 May 2023 in Computer Aided Geometric Design
Verified
Journal Article
Closed access
ZQZheng Qin
Zheng Qin
CWChangjian Wang
Changjian Wang
YPYuxing Peng
Yuxing Peng
KXKai Xu
Kai Xu