Qian Zheng 郑 乾

Assistant Professor

College of Computer Science and Technology,
Zhejiang University, Hangzhou, China.
Email: qianzheng@zju.edu.cn
Official Academic Profile: [En][中文]


I'm an Assistant Professor (百人计划研究员) at the College of Computer Science and Technology, Zhejiang University, and work closely with Prof Gang Pan and Prof Huajin Tang . I received my BEng (2011) and PhD (2017, supervisor: Prof Gang Pan) degrees in computer science from Zhejiang University. From 2018 to 2022, I was a Research Fellow at the ROSE Lab, Nanyang Technological University and worked closely with Prof Boxin Shi, Prof Xudong Jiang, and Prof Alex Kot.

I have co-authored 72 peer-reviewed papers, with 15 papers in the IEEE journals and 38 papers in top conferences of CVPR/ICCV/ECCV/NeurIPS/ICML/ICLR/AAAI/IJCAI/MM. I was a recipient of the ACM Rising Star Award (Hangzhou Chapter, 2024) and currently serves as an Associate Editor for IEEE Transactions on Cognitive and Developmental Systems and Neurocomputing.

My research interests include Neuromorphic Computing, Computer vision, Machine Learning, with special emphasis on: Spiking Neural Networks (e.g., training methods, spiking LLM), Neuromorphic Camera (e.g., event camera based low-level vision), Stereo Vison (e.g., photometric stereo, NeRF, 3DGS).

常年招收: 博士后、博士、硕士、本科实习生,欢迎邮件联系。希望你:

🔥 News [Click to Expand]

📚 Selected Works [Google Scholar]

Neuromorphic Computing: Spiking Neural Networks, Event Camera, Brain Data Processing

E-NeMF: Event-based Neural Motion Field for Novel Space-time View Synthesis of Dynamic Scenes
Yan Liu, Zehao Chen, Haojie Yan, De Ma, Huajin Tang, Qian Zheng*, Gang Pan.
International Conference on ComputerVision (ICCV), Oct 2025 [paper][code] (coming soon...)
  • Mitigating the impact of noise and sparsity brought by event streams for event-guided novel view-time synthesis
  • A carefully designed framework with novel Parametric Motion Representation, Flow Prediction Modeule, and Temporal-Neighbor Alignment
Training High Performance Spiking Neural Network by Temporal Model Calibration
Jiaqi Yan, Changping Wang, De Ma, Huajin Tang, Qian Zheng*, Gang Pan*.
International Conference on Machine Learning (ICML), Jul 2025 [paper][code] (coming soon...)
  • Exploit spiking neural networks' temporal heterogeneity through logit gradient analysis
  • Highest reported SNN accuracy (up to Jun 2025): 85.83% (ImageNet-1K) and 87.63±0.15% (CIFAR10-DVS)
EDyGS: Event Enhanced Dynamic 3D Radiance Fields from Blurry Monocular Video
Mengxu Lu#, Zehao Chen#, De Ma*, Huajin Tang, Qian Zheng*, Gang Pan.
International Joint Conference on Artificial Intelligence (IJCAI), Aug 2025 [paper][code] (coming soon...)
  • Event-enhanced dynamic 3DGS model taking the input of motion-blurred monocular video
  • EReconstruct the motion mask field and separate static and dynamic regions
EvSTVSR: Event Guided Space-Time Video Super-Resolution
Haojie Yan, Zhan Lu, Zehao Chen, De Ma*, Huajin Tang, Qian Zheng*, Gang Pan.
Proceedings of the Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Feb 2025 [paper][code] (coming soon...)
  • Event-Guided space-time video super-resolution with fewer adjacent frames
  • Excel in handling large motion scenarios
EvHDR-GS: Event-guided HDR Video Reconstruction with 3D Gaussian Splatting
Zehao Chen, Zhanfeng Liao, De Ma, Huajin Tang, Qian Zheng*, Gang Pan*.
Proceedings of the Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Feb 2025 [paper][code] (coming soon...)
  • Ensure consistent brightness for HDR video reconstruction
  • Achieve LDR-to-HDR transformation with single-exposure LDR frames
EvHDR-NeRF: Building High Dynamic Range Radiance Fields with Single Exposure Images and Events
Zehao Chen, Zhanfeng Liao, De Ma, Huajin Tang, Qian Zheng*, Gang Pan*.
Proceedings of the Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Feb 2025 [paper][code] (coming soon...)
  • Reconstruct HDR radiance field even if input images are degraded and are single-exposured
  • Reconstruct Camera Response Function (CRF) from single-exposure images
FEEL-SNN: Robust Spiking Neural Networks with Frequency Encoding and Evolutionary Leak Factor
Mengting Xu, De Ma, Huajin Tang, Qian Zheng*, Gang Pan*.
Conference on Neural Information Processing Systems (NeurIPS), Dec 2024 [paper][code]
  • A unified framework for SNN robustness analysis
  • An inherentrobust SNN method interoperable with other methods, such as adversarial training
Spiking GS: Towards High-Accuracy and Low-Cost Surface Reconstruction via Spiking Neuron-based Gaussian Splatting
Weixing Zhang#, Zongrui Li#, De Ma, Huajin Tang, Xudong Jiang, Qian Zheng*, Gang Pan.
arXiv preprint arXiv:2410.07266 (Arxiv), Oct 2024 [paper][code]
  • Spiking neuron to reduce excessive Gaussians
  • Faster, lower storage, and higher accuracy 3DGS-based surface reconstruction
  • Stable performance superiority of bio-inspired neural computation over artificial neuron-based computation on core AI tasks
Event-ID: Intrinsic Decomposition Using an Event Camera
Zehao Chen#, Zhan Lu#, De Ma, Huajin Tang, Qian Zheng*, Gang Pan*.
ACM International Conference on Multimedia (MM), Oct 2024 [paper][code] (coming soon...)
  • Event-based model establishes relationship between events and intrinsic components
  • Multi-view consistency of events to extract specular-related clues
  • Event-guided intrinsic decomposition framework enables relighting under extreme conditions
Spiking NeRF: Representing the Real-World Geometry by a Discontinuous Representation
Zhanfeng Liao, Yan Liu, Qian Zheng*, Gang Pan*.
Proceedings of the Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Feb 2024 (Oral) [paper][code][VALSE论文速览]
  • An ANN-SNN hybrid MLP for NeRF-based 3D surface reconstruction
  • Demonstrate the superiority of spiking neuron on 3D surface representation
  • Stable performance superiority of bio-inspired neural computation over artificial neuron-based computation on core AI tasks
Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANN
Yangfan Hu#, Qian Zheng#, Xudong Jiang, Gang Pan*.
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 45, No. 12, Dec 2023 [paper][code]
  • An ANN2SNN conversion method with high performance and low time step
  • Highest reported SNN accuracy (up to Jun 2025): object detection (mAP: 73.43%, time steps: 7, PASCAL VOC 2007), and semantic segmentation (mIoU: 69.7%, time steps: 15, PASCAL VOC 2012)
Alleviating the Semantic Gap for Generalized fMRI-to-Image Reconstruction
Tao Fang, Qian Zheng*, Gang Pan.
Conference on Neural Information Processing Systems (NeurIPS), Dec 2023 (Spotlight, 378/12343) [paper][code]
  • Alleviate the semantic gap within known and unknown semantic subspaces
  • A generalized fMRI-to-image reconstruction method that adaptively weights the semantic and structural information
Indoor Lighting Estimation using an Event Camera
Zehao Chen#, Qian Zheng#, Peisong Niu, Huajin Tang, Gang Pan*.
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2021 [paper][code](coming soon...)
  • Event camera captures environmental dynamics during light-activation transients
  • Alleviate illumination-distance ambiguity from the inverse-square law in optical imaging
  • First attempt to build reflectance model using event streams

Stereo Vision: Photometric Stereo, NeRF, 3DGS

Revisiting Supervised Learning-Based Photometric Stereo Networks
Xiaoyao Wei, Zongrui Li*, Binjie Ding, Boxin Shi, Xudong Jiang, Gang Pan, Yanlong Cao*, Qian Zheng*
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Apr 2025 [paper][code][推文]
  • Answer three fundamental questions: 1) Waht is the desired deep feature? 2) How to resolve PS challenges? 3) What is the desired network architecture?
  • A solution based on answers that achieves SOTA performance on several PS benchmarks
Spin-UP: Spin Light for Natural Light Uncalibrated Photometric Stereo
Zongrui Li#, Zhan Lu#, Haojie Yan, Boxin Shi, Gang Pan, Qian Zheng*, Xudong Jiang
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2024 [paper][code]
  • A novel setup for Natural Light Uncalibrated Photometric Stereo
  • A light prior that leverages object's occluding boundaries for reliable environment light
DANI-Net: Uncalibrated Photometric Stereo by Differentiable Shadow Handling, Anisotropic Reflectance Modeling, and Neural Inverse Rendering
Zongrui Li, Qian Zheng*, Boxin Shi, Gang Pan, Xudong Jiang
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2023 [paper][code]
  • A differentiable shadow handling method and an anisotropic reflectance model
  • A self-supervised framework that simultaneously optimizes shape, anisotropic reflectance, shadow map, and light conditions
Pano-NeRF: Synthesizing High Dynamic Range Novel Views with Geometry from Sparse Low Dynamic Range Panoramic Images
Zhan Lu, Qian Zheng*, Boxin Shi, Xudong Jiang
Proceedings of the Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Feb 2024 [paper][code]
  • An interesting idea of the proposed irradiance fields
  • Irradiance fields can be integrated into and jointly optimized with radiance fields to recover the geometry and HDR of a panoramic image
SPLINE-Net: Sparse Photometric Stereo through Lighting Interpolation and Normal Estimation Networks
Qian Zheng#*, Yiming Jia#, Boxin Shi*, Xudong Jiang, Ling-Yu Duan, Alex C. Kot
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2019 [paper][code]
  • Sparse photometric stereo by generation
  • Convert insights of global illumination effects and isotropic reflectance to loss fuction based on observation map
Numerical Reflectance Compensation for Non-Lambertian Photometric Stereo
Qian Zheng, Ajay Kumar*, Boxin Shi, Gang Pan
IEEE Transactions on Image Processing (TIP), Vol 28, Iss 7, Jul 2019) [paper][code]
  • Reformulate non-Lambertian photometric stereo problem using the angular error to close the gap between evaluation and optimization
  • Numerical compensation scheme that solves photometric stereo problem by minizing the angular error

Visual Generation, Reinformance Learning, and Computational Photography

Connecting Consistency Distillation to Score Distillation for Text-to-3D Generation
Zongrui Li#, Minghui Hu#, Qian Zheng*, Xudong Jiang.
European Conference on Computer Vision (ECCV), Sep 2024 [paper][code]
  • Identify 3 problems in the PF-ODEs-based score distillation method by connecting consistency distillation to score distillation
  • An improved score distillation method to enhance details and fidelity of generated 3D assets
Learning to Manipulate Artistic Images
Wei Guo#, Yuqi Zhang#, De Ma*, Qian Zheng*
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Feb 2024 [paper][code][VALSE论文速览]
  • An arbitrary Style Image Manipulation Network to achieve zero-shot style image manipulation
  • Balance computational efficiency and high resolution
Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization
Juntao Dai, Taiye Chen, Yaodong Yang*, Qian Zheng*, Gang Pan
International Conference on Learning Representations (ICLR), Apr 2025 [paper]
  • Enable the detection of whether a response is OOD for the reward model.
  • The first method that uses value regularization to address reward over-optimization and penalizes OOD values without affecting ID ones
Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation
Juntao Dai, Yaodong Yang, Qian Zheng*, Gang Pan*
International Conference on Machine Learning (ICML), Jul 2024 [paper]
  • A method to estimate finite-horizon non-discounted constraints in Safe RL tasks
  • A deep Safe RL algorithm to address tasks with finite-horizon constraints
Augmented Proximal Policy Optimization for Safe Reinforcement Learning
Juntao Dai#, Jiaming Ji#, Long Yang, Qian Zheng*, Gang Pan*
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Feb 2023 [paper]
  • Construct multiplier-penalty function that dampens cost oscillation for stable convergence while being equivalent to the primal constrained problem to precisely control safety costs
  • Provide an implementation based above construction
Single Image Reflection Removal with Absorption Effect
Qian Zheng*, Boxin Shi*, Jinnan Chen, Xudong Jiang, Ling-Yu Duan, Alex C. Kot
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2021 [paper][code]
  • Reflection-contaminated image formation model considering absorption effect
  • Superior performance advantage on the recovery of overall intensity
Panoramic Image Reflection Removal
Yuchen Hong#, Qian Zheng#, Lingran Zhao, Xudong Jiang, Alex C. Kot, Boxin Shi*
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2021 [paper]
  • Relieve the content ambiguity for reflection removal using a panoramic image
  • Solve the geometric and photometric misalignment between reflection scenes in panoramic and glass-reflected views
  • Generalizes well to casual users without panoramic cameras
What does Plate Glass Reveal about Camera Calibration?
Qian Zheng*, Jinnan Chen, Zhan Lu, Boxin Shi*, Xudong Jiang, Kim-Hui Yap, Ling-Yu Duan, and Alex C. Kot
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2020 [paper][code]
  • First work addresses the single image camera calibration problem in the context of glass reflection
  • 320 reflection-contaminated images with their calibration parameters
  • Alleviate the ill-posedness of single image panoramic image estimation

🌏 Activities

Associate Editor
IEEE Transactions on Cognitive and Developmental Systems (2024.12 - present)
Neurocomputing (2023.10 - present)
Reviewer
TPAMI, IJCV, TIP, TNNLS, TCSVT, TMM
CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, SIGGRAPH, AAAI, IJCAI, ACM MM
Committee Member
Finance Chair: IEEE CIS-RAM 2024
The Branch of Consciousness Science of the Chinese Cognitive Science Society (中国认知科学学会意识科学分会委员)
Young Professionals Committee of Chinese Association for Artificial Intelligence (中国人工智能协会青年工作委员会委员)
The Branch of Brain-computer Interface & Interaction of Chinese Neuroscience Society (中国神经科学学会脑机分会委员)

📆 Teaching

Theory of Computation (Undergraduate)
2024-2025 Fall&Winter, Zhejiang University
2023-2024 Fall&Winter, Zhejiang University
Machine Learning (Graduate)
2023-2024 Summer, Zhejiang University
2022-2023 Summer, Zhejiang University

🎓 Alumni

Juntao Dai (PhD Student, 2025.06)
Co-supvervised with Prof Gang Pan
During his doctoral studies, we published papers at AAAI 2023, ICML 2025, and ICLR 2025
Upon graduation, Juntao joined Beijing Academy of Artificial Intelligence (BAAI)
Zehao Chen (PhD Student, 2024.12)
Upon graduation, Zehao continued to work in my group as postdoc (postdoc PIs: Prof Gang Pan and Prof Zengwei Zheng)
During his doctoral studies, Zehao won Hangzhou Innovation and Entrepreneurship Competition (3rd Prize, 7.9%)
Zehao was awarded Postdoctoral Innovation Talent Support Program (博新计划)
Tao Fang (PhD Student, 2024.03)
Co-supvervised with Prof Gang Pan and Prof Yu Qi
During his doctoral studies, we published papers at AAAI 2023 and NeurIPS 2023
All publications during his doctoral studies were either oral (NeurIPS 2021, AAAI 2023) or spotlight (NeurIPS 2023)
Upon graduation, Tao Fang joined Alibaba Cloud
Dong Xing (PhD Student, 2023.12)
Co-supvervised with Prof Gang Pan and Prof Bo An
During his doctoral studies, we published papers at IJCAI 2021 (oral), IJCAI 2022 (oral), and ICML 2023
Upon graduation, Dong Xing joined Optiver
Yangfan Hu (PhD Student, 2023.06)
Co-supvervised with Prof Gang Pan
During his doctoral studies, we published papers at TPAMI 2023 and TCDS 2024
Upon graduation, Yangfan joined Zhejiang University of Finance and Economics as a faculty
Zhanfeng Liao (Master Student, 2024.03)
Co-supvervised with Prof Gang Pan.
During his undergraduate studies, we published a paper at AAAI 2024 (oral)
Upon graduation, Zhanfeng pursued PhD degree at Tsinghua University, supervised by Prof Yebin Liu
Junzhou Chen (Master Student, 2024.03)
Co-supvervised with Prof Gang Pan.
Upon graduation, Junzhou joined Wenzhou Bureau of Natural Resources and Planning
Yuqi Zhang (Master Student, 2023.03)
Co-supvervised with Prof Gang Pan
During her undergraduate studies, we published a paper at CICAI 2022, our follow-up work published at AAAI 2024
Upon graduation, Yuqi joined ByteDance
Zhiyuan Ma (Undergraduate Student, 2025.06)
Zhiyuan was awarded 2025 Excellent Undergraduate Dissertation of Zhejiang University
Upon graduation, Zhiyuan pursued PhD degree at Tsinghua University, supervised by Prof Sen Song