I am a fourth-year Ph.D. student at Beijing Jiaotong University (BJTU) in MePro, supervised by Prof. Chunyu Lin and Prof. Yao Zhao. Recently, I have been fortunate to work with Prof. Shuaicheng Liu at University of Electronic Science and Technology of China (UESTC). Prior to that, I received my Bachelor degree at Computer Science and Technology from BJTU.
My research interests cover a range of computer vision and deep learning. I have authored or co-authored about 20 academic papers in top-tier international conferences and journals, including CVPR, ICCV, ECCV, TPAMI, TIP, TMM, TCSVT, etc. I'm open to any kind of collaboration. Please feel free to contact me through email.
nielang [at] bjtu.edu.cn Google Scholar Github
Recently, I've been interested in exploring various image warps with deep learning, such as homography, mesh, optical flow, thin-plate spline, etc. These deep warps provide new solutions for classic computer vision tasks (e.g. image stitching, video stabilization, and so on) and demonstrate impressive performance. The specific intersts are listed below:
image/video stitching, image rectangling, homography estimation, video stabilization
panoramic objection detection, semantic segmentation, depth estimation, layout estimation
multi-view stereo (MVS), MVS + NeRF
Deep Learning for Camera Calibration and Beyond: A Survey
Kang Liao, Lang Nie, Shujun Huang, Chunyu Lin, Jing Zhang, Yao Zhao, Moncef Gabbouj, Dacheng Tao
[Paper]
[Project Page]
TG-Pose: Delving into Topology and Geometry for Category-level Object Pose Estimation
Yue Zhan, Xin Wang, Lang Nie, Yang Zhao, Tangwen Yang, Qiuqi Ruan
IEEE Transactions on Multimedia (TMM)
[Paper]
[Code]
[Project Page]
RecStitchNet: Learning to Stitch Images with Rectangular Boundaries
Yun Zhang, Yu-Kun Lai, Lang Nie, Fang-Lue Zhang, Lin Xu
Computational Visual Media Journal (CVMJ)
[Paper]
S-OmniMVS: Incorporating Sphere Geometry into Omnidirectional Stereo Matching
Zisong Chen, Chunyu Lin, Lang Nie, Zhijie Shen, Kang Liao, Yuanzhouhan Cao, Yao Zhao
ACM Multimedia (ACM MM). (Oral presentation)
[Paper]
As-Deformable-As-Possible Single-image-based View Synthesis without Depth Prior
Chunlan Zhang, Chunyu Lin, Kang Liao, Lang Nie, Yao Zhao
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
[Paper]
Complementary Bi-directional Feature Compression for Indoor 360° Semantic Segmentation with Self-distillation
Zishuo Zheng, Chunyu Lin, Lang Nie, Kang Liao, Zhijie Shen, Yao Zhao
Winter Conference on Applications of Computer Vision (WACV)
[Paper]
Deep Rectangling for Image Stitching: A Learning Baseline
Lang Nie, Chunyu Lin, Kang Liao, Shuaicheng Liu, Yao Zhao
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). (Oral presentation)
[Paper]
[Code]
[Dataset]
[Video]
[Chinese Blog]
SivsFormer: Parallax-Aware Transformers for Single-image-based View Synthesis
Chunlan Zhang, Chunyu Lin, Kang Liao, Lang Nie, Yao Zhao
IEEE Conference on Virtual Reality and 3D User Interfaces (VR)
[Paper]
Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images
Lang Nie, Chunyu Lin, Kang Liao, Shuaicheng Liu, Yao Zhao
IEEE Transactions on Image Processing (TIP)
[Paper]
[Code]
[Dataset]
[Chinese Blog]
Learning Edge-Preserved Image Stitching from Multi-Scale Deep Homography
Lang Nie, Chunyu Lin, Kang Liao, Yao Zhao
Neurocomputing (NEUCOM)
[Paper]