Zhiqiang Yan

Zhiqiang Yan

Auto-generated profile, based on publicly available information

Zhiqiang Yan

PCA Laboratory, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
30 October 2022
Verified
Book Chapter
Closed access
PDF file
ZYZhiqiang Yan
Zhiqiang Yan
KWKun Wang
Kun Wang
XLXiang Li
Xiang Li
ZZZhenyu Zhang
Zhenyu Zhang
JLJun Li
Jun Li
JYJian Yang
Jian Yang

26 October 2022 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
ZYZhiqiang Yan
Zhiqiang Yan
Kun WangKun Wang
Kun Wang
XLXiang Li
Xiang Li
ZZZhenyu Zhang
Zhenyu Zhang
GLGuangyu Li
Guangyu Li
JYJian Yang
Jian Yang
Depth information is a significant ingredient to visually perceive the physical world. However, mainstream depth sensors, e.g., time-of-flight (ToF) cameras, often measure incomplete and low-resolution depth data, resulting in low-quality visual perception. In this article, we try to address a potentially valuable task, i.e., depth super-resolution (DSR) with incomplete data, which recovers dense and high-resolution depth map from incomplete and low-resolution one. To tackle this task, we introduce a novel incomplete DSR (IDSR) framework, including a primary branch for DSR to recover high-frequency details, and an auxiliary branch for depth completion (DC) to fill missing pixels. More importantly, we propose two modules, joint correlation learning (JCL) and iterative-cross (IC), to enhance the learning of complementary information flows between the two branches. The former module aims to learn the correlative relationships of the two branches, whilst the latter module adequately fuses higher level representations for more precise predictions. Extensive experiments show that our framework is effective and achieves the state-of-the-art performance on the real-world RGB-D-D and the synthetic NYUv2 datasets.

23 October 2022
Verified
Book Chapter
Closed access
PDF file
ZYZhiqiang Yan
Zhiqiang Yan
XLXiang Li
Xiang Li
KWKun Wang
Kun Wang
ZZZhenyu Zhang
Zhenyu Zhang
JLJun Li
Jun Li
JYJian Yang
Jian Yang

19 June 2024 in Visual Intelligence
Verified
Journal Article
Open access
PDF file
ZYZhiqiang Yan
Zhiqiang Yan
YZYupeng Zheng
Yupeng Zheng
DFDeng-Ping Fan
Deng-Ping Fan
XLXiang Li
Xiang Li
JLJun Li
Jun Li
JYJian Yang
Jian Yang
Depth completion is the task of recovering dense depth map from sparse ones, usually with the help of color images. Existing image guided methods perform well on daytime depth perception self-driving benchmarks, but struggle in nighttime scenarios with poor visibility and complex illumination. To address these challenges, we propose a simple yet effective learnable differencing center network (LDCNet). The key idea is to use recurrent inter-convolution differencing (RICD) and illumination affinitive intra-convolution differencing (IAICD) to enhance the nighttime color images and reduce the negative effects of the varying illumination, respectively. RICD explicitly estimates global illumination by differencing two convolutions with different kernels, treating the small-kernel-convolution feature as the center of the large-kernel-convolution feature in a new perspective. IAICD softly alleviates the local relative light intensity by differencing a single convolution, where the center is dynamically aggregated based on neighboring pixels and the estimated illumination map in the RICD. On both nighttime depth completion and depth estimation tasks, extensive experiments demonstrate the effectiveness of our LDCNet, reaching the state of the art.

23 May 2025 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
ZYZhiqiang Yan
Zhiqiang Yan
XLXiang Li
Xiang Li
LHLe Hui
Le Hui
ZZZhenyu Zhang
Zhenyu Zhang
JLJun Li
Jun Li
JYJian Yang
Jian Yang

6 August 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
ZYZhiqiang Yan
Zhiqiang Yan
Kun WangKun Wang
Kun Wang
XLXiang Li
Xiang Li
GGGuangwei Gao
Guangwei Gao
JLJun Li
Jun Li
JYJian Yang
Jian Yang
Depth completion and super-resolution are crucial tasks for comprehensive RGB-D scene understanding, as they involve reconstructing the precise 3D geometry of a scene from sparse or low-resolution depth measurements. However, most existing methods either rely solely on 2D depth representations or directly incorporate raw 3D point clouds for compensation, which are still insufficient to capture the fine-grained 3D geometry of the scene. In this paper, we introduce Tri-Perspective View Decomposition (TPVD) frameworks that can explicitly model 3D geometry. To this end, (1) TPVD ingeniously decomposes the original 3D point cloud into three 2D views, one of which corresponds to the sparse or low-resolution depth input. (2) For sufficient geometric interaction, TPV Fusion is designed to update the 2D TPV features through recurrent 2D-3D-2D aggregation. (3) By adaptively searching for TPV affinitive neighbors, two additional refinement heads are developed for these two tasks to further improve the geometric consistency. Meanwhile, we build novel datasets named TOFDC for depth completion and TOFDSR for depth super-resolution. Both datasets are acquired using time-of-flight (TOF) sensors and color cameras on smartphones. Extensive experiments on TOFDC, KITTI, NYUv2, SUN RGBD, VKITTI, TOFDSR, RGB-D-D, Lu, and Middlebury datasets indicate that our TPVD outperforms previous depth completion and super-resolution methods, reaching the state of the art.