Haoyue Liu-刘昊岳

Biography

I am currently a postdoctoral researcher at Huazhong University of Science and Technology (HUST). Previously, I received my Ph.D. degree in Artificial Intelligence from HUST in 2025, and my M.S. and B.E. degrees from China University of Mining and Technology (CUMT) in 2013 and 2016, respectively.

News

2025.06, Our event-based 4D Gaussian splatting paper has been accepted by ICCV'25.
2025.02, Our event-based video frame interpolation paper has been accepted by CVPR'25.
2025.02, Our event-based dense and continuous optical flow paper has been accepted by CVPR'25.
2024.02, Our work for event-based low-light imaging has been accepted by TPAMI'25.
2024.02, Our work for event-based nighttime HDR imaging has been accepted by CVPR'24.
2024.01, Our work for event-based nighttime optical flow estimation has been accepted by ICLR'24 (Spotlight).
2023.06, We have won 1st place in the track 'Atmospheric Turbulence Mitigation' in the CVPR'23 UG2+ Challenge.

Researches

In dynamic scenes with extreme lighting conditions, the visual signals captured by conventional cameras degrade, posing challenges for scene imaging and perception tasks. Event cameras are a new type of sensor, which independently activates each pixel based on changes in brightness. This sensor offers several significant advantages, including a high dynamic range (120dB) and high temporal resolution (1μs) , providing a novel approach for imaging and perception in extreme lighting environments. We have built a multimodal data acquisition platform and designed efficient machine learning algorithms to train state-of-the-art deep models, achieving the goal of imaging and perception in dynamic scenes with complex lighting.

1. Constructing a paired real low-light event dataset (RLED). Specifically, we design a co-axial imaging system comprising an event camera with a neutral density(ND) filter and a conventional camera, which allows for the simultaneous acquisition of low-light events and high-quality images. RLED provides 64,200 images with corresponding events, capturing events illuminance levels ranging from 0.5 lux to 1000 lux. The research outputs have been published in CVPR 2024 and TPAMI 2025.

2. Constructing a multimodality perception system and a large-scale multimodal dataset. Consisdering the scarcity of all-day and all weather motion datasets, We constructs a RGB-Event-LiDAR-IMU multimodality perception system with spatiotemporal alignment, and builds a large-scale multimodal dataset under various time (e.g., daytime and nighttime) and various weather (e.g., rain, fog and snow). The research outputs are comming soon.

Publications (Google Scholar)

Preprint Papers

Awards

2025.06, Outstanding Graduate.

2021.09-2025.06, First-class Scholarship for Doctoral Students.

2024.12, Merit Student.

2023.12, Active Participants Award in Extracurricular Activities.

2023.06, 1st place in the track 'Atmospheric Turbulence Mitigation' in the CVPR'23 UG2+ Challenge.

2022.12, Excellent Postgraduate Cadre Award.

	NER-Net+: Seeing Motion at Nighttime with an Event Camera. Haoyue Liu, Jinghan Xu, Shihan Peng, Yi Chang, Hanyu Zhou, Yuxing Duan, Lin Zhu, Yonghong Tian, Luxin Yan. IEEE Transactions on Pattern Analysis and Machine Intelligence ( TPAMI* ), 2025.* [PDF] [Code]
	TimeTracker: Event-based Continuous Point Tracking for Video Frame Interpolation with Non-linear Motion. Haoyue Liu, Shihan Peng, Lin Zhu, Yi Chang, Hanyu, Luxin Yan. IEEE Conference on Computer Vision and Pattern Recognition ( CVPR* ), 2025.* [PDF] [supp] [arXiv]
	Event-Structured Modeling and Detection of Faint Space Objects with a Dynamic Vision Sensor. Hao Dong, Zhiwei Shi, Haoyue Liu, Yi Chang, Luxin Yan. Acta Optica Sinica (光学学报), 2025. [PDF]
	Seeing Motion at Nighttime with an Event Camera. Haoyue Liu, Shihan Peng, Lin Zhu, Yi Chang, Hanyu, Luxin Yan. IEEE Conference on Computer Vision and Pattern Recognition ( CVPR* ), 2024.* [PDF] [supp] [arXiv] [Code]
	STD-GS: Exploring Frame-Event Interaction for SpatioTemporal-Disentangled Gaussian Splatting to Reconstruct High-Dynamic Scene. Hanyu Zhou, Haonan Wang, Haoyue Liu, Yuxing Duan, Luxin Yan, Gim Hee Lee. IEEE Conference on Computer Vision and Pattern Recognition ( ICCV* ), 2025.* [arXiv] [Code]
	Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Scene Optical Flow. Hanyu Zhou, Haonan Wang, Haoyue Liu, Yuxing Duan, Yi Chang, Luxin Yan. IEEE Conference on Computer Vision and Pattern Recognition ( CVPR* ), 2024.* [PDF] [arXiv]
	Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flow. Hanyu Zhou, Yi Chang, Haoyue Liu, Wending Yan, Yuxing Duan, Zhiwei Shi, Luxin Yan. International Conference on Learning Representations ( ICLR* ), Spotlight, 2024.* [PDF] [arXiv]

Haoyue Liu 刘昊岳

Postdoctoral Researcher

Biography

Interests

News

Researches

Publications (Google Scholar)

Preprint Papers

Awards

Academic Services