
Research portfolio · Suzhou, China · 2026
Qinfeng Zhu朱钦峰
Ph.D. researcher exploring how machines perceive remote sensing.
I am a Ph.D. student at Xi'an Jiaotong-Liverpool University and the University of Liverpool, advised by Dr. Lei Fan. I received an MRes in Computer Science from the University of Liverpool in 2023.
Research internships
Open to internship opportunities.
After graduation
Seeking full-time roles in academia or industry.
Research atlas
Understanding the world,
pixel by point.
My work connects sensing, representation learning and scene understanding across 2D images, panoramic imagery and 3D point clouds.
Open the interactive atlas ↗
Remote Sensing
Learning rich representations from aerial, satellite and multispectral observations.

3D Computer Vision
Point-cloud learning and fine-grained urban scene understanding.

Panoramic Vision
Geometry-aware representation learning for distortion-robust, rotation-consistent 360° scene understanding.

Multimodal Fusion
Combining complementary sensors to build more robust perception systems.

Semantic Segmentation
Pixel-level and point-level reasoning for indoor, urban and environmental scenes.

Data Augmentation
Strategies that improve generalization across scarce and imbalanced data.

Deep Learning
Modern architectures for reliable and explainable visual intelligence.
Selected work
Featured publications.
A curated selection spanning panoramic perception, point-cloud understanding, remote sensing and multispectral learning.
Search all publications ↗

Panoramic Scene Understanding: A Survey from Distortion-Aware Engineering to Sphere-Native Modeling.

SO3UFormer: Learning Intrinsic Spherical Features for Rotation-Robust Panoramic Dense Prediction.

Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey.

ClassWise-CRF: Category-Specific Fusion for Enhanced Semantic Segmentation of Remote Sensing Imagery.

Rethinking Scanning Strategies with Vision Mamba in Semantic Segmentation of Remote Sensing Imagery.

IndoorMS: A Multispectral Dataset for Semantic Segmentation in Indoor Scene Understanding.
Complete record
Additional publications.
9 further papers · 16 publications shown on this page
-
A generalised pre-training strategy for deep learning networks in semantic segmentation of remotely sensed images.
Yuan Fang, Yuanzhi Cai, Jagannath Aryal, Qinfeng Zhu, Hong Huang, Cheng Zhang, Lei Fan
-
SwinMamba: A hybrid local-global mamba framework for enhancing semantic segmentation of remotely sensed images.
Qinfeng Zhu, Han Li, Liang He, Lei Fan
-
Enhancing Environmental Monitoring through Multispectral Imaging: The WasteMS Dataset for Semantic Segmentation of Lakeside Waste.
Qinfeng Zhu, Ningxin Weng, Lei Fan, Yuanzhi Cai
-
MSCrackMamba: Leveraging Vision Mamba for Crack Detection in Fused Multispectral Imagery.
Qinfeng Zhu, Yuan Fang, Lei Fan
-
Samba: Semantic Segmentation of Remotely Sensed Images with State Space Model.
Qinfeng Zhu, Yuanzhi Cai, Yuan Fang, Yihan Yang, Cheng Chen, Lei Fan, Anh Nguyen
-
Evaluating the Impact of Point Cloud Colorization on Semantic Segmentation Accuracy.
Qinfeng Zhu, Jiaze Cao, Yuanzhi Cai, Lei Fan
-
Seg-LSTM: Performance of xLSTM for Semantic Segmentation of Remotely Sensed Images.
Qinfeng Zhu, Yuanzhi Cai, Lei Fan
-
Algorithm-Driven Extraction of Point Cloud Data Representing Bottom Flanges of Beams in a Complex Steel Frame Structure for Deformation Measurement.
Yang Zhao, Dufei Wang, Qinfeng Zhu, Lei Fan, Yuanfeng Bao
All 16 publications are visible above. The dedicated library adds year, venue and topic filters, direct links and one-click BibTeX copying.
Open searchable library ↗Research infrastructure
Datasets built for
real-world perception.
Curated benchmarks that bridge spectral sensing, dense annotation and practical scene understanding.
View all projects ↗
Explore dataset ↗
SemanticUrban
A large-scale, high-resolution terrestrial laser-scanning dataset for accurate urban scene understanding.
- Scenes
- 150
- Points
- ~4B
- Classes
- 23
Explore dataset ↗
IndoorMS
A dedicated multispectral benchmark for semantic segmentation across diverse indoor scenes.
- Buildings
- 17
- Classes
- 19
- Best mIoU
- 72.90
Latest signals
Research
news.
Recent publication milestones and dataset releases. The complete timeline lives in the Research Atlas.
View timeline ↗SemanticUrban has been accepted by Expert Systems with Applications.
SwinMamba has been accepted by Digital Signal Processing.
ClassWise-CRF has been accepted by Neural Networks 2026.
IndoorMS has been accepted by IEEE Sensors Journal.
Academic community
Service &
peer review.
Contributing to rigorous and constructive evaluation across computer vision, machine learning and remote sensing.
Membership
- Senior MemberISAC
- MemberIEEE
Journal reviewer
- IEEE TNNLS · TCSVT · T-ITSNeural networks, video technology and intelligent transportation
- ISPRS JPRS · Scientific DataPhotogrammetry, remote sensing and research datasets
- PR · NN · ESWA · EAAIComputer vision and applied artificial intelligence
- Additional journalsNeurocomputing, IEEE Sensors Journal, IEEE Access, Journal of Supercomputing, Complex & Intelligent Systems, Computers & Graphics, Applied Intelligence
Conference & workshop reviewer
International Conference on Learning Representations · AAAI Conference on Artificial Intelligence · International Joint Conference on Artificial Intelligence · Machine Learning for Health · IEEE/CVF Winter Conference on Applications of Computer Vision · International Joint Conference on Neural Networks · IEEE International Symposium on Biomedical Imaging · IEEE Symposium on Computers & Informatics · International Conference on Artificial Intelligence and Human-Computer Interaction
Have an idea?
Let's explore it
together.
I am always open to research collaborations, thoughtful conversations and new opportunities.
zhuqinfeng1999@gmail.com ↗Institutional · qinfeng.zhu21@student.xjtlu.edu.cn