Zhiqiang Yan

I am a Phd student at PCALab of Nanjing University of Science and Technology (NJUST) from 2020 to 2024, advised by Prof. Jian Yang and co-advised by Prof. Jun Li.

I obtained my B.E. degree in 2018 from NJUST.

Email  /  CV  /  GitHub  /  Google Scholar  /  WeChat

I am looking for a postdoctoral position that will allow me to continue my research and expand my academic skills. I expect to graduate in June 2024. If you are interested in my profile, please contact me. Thank you.

My research interests include computer vision and machine learning, especially on depth estimation, depth completion, depth super-resolution, and NeRF rendering. These tasks are crucial for various applications, such as self-driving, robotic vision, and related 3D visual perception. I am also fascinated by the task of 3D occupancy prediction.

TPVD decomposes 3D point cloud into three views to capture the fine-grained 3D geometry of scenes. TPV Fusion and GSPN are proposed to refine the depth. Furthermore, we build a novel depth completion dataset named TOFDC, acquired by the time-of-flight (TOF) sensor and the color camera on smartphones.

To address the issues of texture interference and edge inaccuracy in GDSR, for the first time, SPFNet introduces the priors surface normal and semantic map from large-scale models. As a result, SPFNet achieves state-of-the-art performance.

On the basis of RigNet, in semantic guidance branch, RigNet++ introduces large-scale model SAM, to supply depth with semantic prior. In image guidance branch, RigNet++ design a dense repetitive hourglass network (DRHN) to provide powerful contextual instruction for depth prediction. In addition, RigNet++ proposes a region-aware spatial propagation network (RASPN) for further depth refinement based on the semantic prior constraint.

SGNet introduces a novel perspective that exploits the gradient and frequency domains for the structure enhancement of DSR task, surpassing the five state-of-the-art methods by 16% (RGB-D-D), 24% (Middlebury), 21% (Lu) and 15% (NYU-v2) in average.

This paper proposes AltNeRF, a novel framework designed to create resilient NeRF representations using self-supervised monocular depth estimation (SMDE) from monocular videos, without relying on known camera poses. Extensive experiments showcase the compelling capabilities of AltNeRF in generating high-fidelity and robust novel views that closely resemble reality.

Standard MSE or MAE loss function is commonly used in limited field-of-vision depth completion, treating each pixel equally under a basic assumption that all pixels have same contribution during optimization. However, the assumption is inapplicable to panoramic data due to its latitude-wise distortion and high uncertainty nearby textures and edges. To handle these challenges, this paper proposes the distortion and uncertainty aware loss (DUL) that consists of a distortion-aware loss and an uncertainty-aware loss.

DesNet first introduces a decomposed scale-consistent learning strategy, which disintegrates the absolute depth into relative depth prediction and global scale estimation, contributing to individual learning benefits. Extensive experiments show the superiority of DesNet on KITTI benchmark, ranking 1st and surpassing the second best more than 12% in RMSE.

RigNet explores a repetitive design for depth completion to tackle the blurry guidance in image and unclear structure in depth. Extensive experiments show that RigNet achieves superior or competitive results on KITTI benchmark and NYUv2 dataset.

For the first time, we enable the masked pre-training in a Convolution-based multi-modal task, instead of the Transformer-based single-modal task. What's more, we introduce the panoramic depth completion, a new task that facilitates 3D reconstruction.

Motivated by pratical applications, this paper introduces a new task, i.e., incomplete depth super-resolution (IDSR), which recovers dense and high-resolution depth from incomplete and low-resolution one.

For the first time, RNW introduces a nighttime self-supervised monocular depth estimation framework. The low visibility brings weak textures while the varying illumination breaks brightness-consistency assumption. To address these problems, RNW proposes the novel Priors-Based Regularization, Mapping-Consistent Image Enhancement, and Statistics-Based Mask.

• 2023.10, National Scholarship (Top 2%), NJUST;

• 2022.10, Hua Wei Scholarship (Top 1%), NJUST;

• Conference reviewer: CVPR, ICCV, ECCV, 3DV, AAAI, ACCV

This webpage is forked from Junkai Fan. Thanks to him!