Challenge & Website Launch
May 10, 2026
Important Dates
Training / Validation Set Release
May 12, 2026
Test Set & Evaluation Server Online
June 20, 2026
Submission Start
July 01, 2026
Challenge Results Announcement
July 5, 2026
Abstract Registration
July 15, 2026
Submission Deadline
July 20, 2026
Notification to Authors
August 5, 2026
Camera-ready Deadline
August 12, 2026
ECCV 2026 Workshop
Sept 8–13, 2026
About
Our workshop focuses on research at the intersection of event-based sensing and multimodal vision, spanning the full pipeline from sensing systems and low-level imaging to perception and high-level understanding.
Sensing Systems
- Event-based and neuromorphic vision with multimodal visual sensing.
- Hybrid systems with event cameras, RGB, LiDAR, IMU, and language.
- Datasets, simulators, benchmarks, and annotation pipelines.
- Spatial-temporal calibration, synchronization, and alignment.
Low-Level Imaging
- Event-guided illumination modeling and brightness adjustment.
- Enhancement under low-light, HDR, blur, noise, and reconstruction scenarios.
- Image or intensity reconstruction and physics-aware video synthesis.
- Illumination-aware representations and sensor-aware modeling.
Mid-Level Perception
- Optical flow, depth, visual odometry, SLAM, and 3D reconstruction.
- Segmentation, detection, feature tracking, and visual tracking.
- Multimodal fusion for challenging dynamic environments.
- Model-based, embedded, and learning-based event-driven perception.
High-Level Understanding
- Visual grounding, action understanding, and spatiotemporal reasoning.
- Event-based MLLMs and event-stream vision-language learning.
- Autonomous driving, robotics, and embodied intelligence.
- Cross-modal reasoning with asynchronous sparse event representations.
Computing and Hardware
- Novel event cameras, neuromorphic processors, and event-based systems.
- Efficient architectures, including state-space and lightweight designs.
- Sensor-aware learning grounded in event generation mechanisms.
Applications
- Computational imaging and industrial inspection.
- Autonomous driving, robotics, AR/VR, and edge intelligence.
- Deployment-oriented solutions for dynamic real-world scenarios.
Call for Papers
Submission Format
All submissions must follow the ECCV 2026 official paper template and formatting guidelines. View the official submission policies.
Full Paper Track
8–14 pagesFor substantial, original research contributions with a complete technical and experimental presentation. References are excluded from the page limit.
- Welcomes original research, benchmarks, systems, datasets, and application-oriented work related to the workshop themes.
- Open to the broader research community and not limited to challenge participants.
- Relevant areas include event-based vision, multimodal perception, foundation models, embodied AI, robotics, and related topics.
- Submissions should provide clear technical contributions, sufficient experimental validation, and a complete discussion of the proposed study.
Technical Report Track
4–6 pagesFor concise technical contributions, especially workshop challenge solutions. References are excluded from the page limit.
- Primarily intended for challenge participants, while remaining open to other focused technical contributions.
- Suitable for challenge solutions, system designs, implementation details, practical insights, preliminary methods, and technical findings.
- Reports should clearly describe the proposed approach and present all available evaluation results.
- Comprehensive validation, extensive ablations, and complete theoretical analysis are not required to match the level expected of Full Papers.
Review Process
All submissions will undergo peer review by the Workshop Program Committee. Submissions will be assessed according to the selected track and the following criteria: Workshop Relevance, Technical Quality, Clarity of Presentation, Track Appropriateness.
Challenges
Low-Level Imaging Challenge: Event-Guided Brightness Adjustment with SEE 600K
A benchmark challenge for event-guided brightness adjustment under broad lighting conditions, including low light, over-exposure, mixed illumination, and high-contrast scenes. Participants use RGB frames and event streams to restore well-exposed and structurally faithful images.
Dataset: SEE-600K
Challenge Details Competition Page Dataset Baseline Code Evaluation Server Leaderboard
Low-Level Imaging Challenge: Event-Guided High-frame-rate Video Reconstruction on EventAid and ERF-X170FPS
A benchmark challenge for event-guided high-frame-rate video reconstruction. Participants use low-frame-rate RGB videos and event streams to recover high-frame-rate videos with accurate restoration of fast motion.
Dataset: EventAid, ERF-X170FPS
Mid-Level Perception Challenge: Event-Guided Monocular Depth Estimation with CoSEC
A benchmark challenge for event-guided monocular depth estimation in real-world scenes. Participants use RGB frames and event streams to predict accurate depth maps.
Dataset: CoSEC
Mid-Level Perception Challenge: Event-Guided Semantic Segmentation with CoSEC
A benchmark challenge for event-guided semantic segmentation in real-world scenes. Participants use RGB frames and event streams to predict pixel-level semantic labels.
Dataset: CoSEC
High-Level Understanding Challenge: Event-Guided Spatial Reasoning with EventBench
This challenge benchmarks MLLMs' spatial reasoning on event-based vision, focusing on object counting, absolute distance estimation, and spatial relationship reasoning.
Dataset: EventBench
High-Level Understanding Challenge: Event Stream Understanding with EventBench
This challenge aims to systematically evaluate and push the boundaries of MLLMs in understanding and reasoning over event-based vision data. Our goal is to foster the development of robust, parameter-efficient multi-modal models capable of deep semantic comprehension, spatial-temporal reasoning, and fine-grained recognition within complex event streams.
Dataset: EventBench
Schedule
| Time | Session | Speakers / Details |
|---|---|---|
| 08:00 - 08:15 | Opening and Welcome | Workshop introduction and opening remarks |
| 08:15 - 09:45 | Invited Talks Session I |
08:15 - 08:45 Prof. Kostas Daniilidis 08:45 - 09:15 Prof. Guillermo Gallego 09:15 - 09:45 Prof. Priyadarshini Panda |
| 09:45 - 10:00 | Coffee Break | |
| 10:00 - 11:00 | Challenge Session |
Six Challenge Track winner presentations, 10 min each |
| 11:00 - 12:30 | Invited Talks Session II |
11:00 - 11:30 Prof. Laurent Kneip 11:30 - 12:00 Prof. Shintaro Shiba 12:00 - 12:30 Prof. Federico Becattini |
| 12:30 - 13:30 | Lunch Break | |
| 13:30 - 15:00 | Invited Talks Session III |
13:30 - 14:00 Dr. Daniel Gehrig 14:00 - 14:30 Prof. Liyuan Pan 14:30 - 15:00 Prof. Bo Mu |
| 15:00 - 15:15 | Coffee Break | |
| 15:15 - 16:15 | Invited Talks Session IV |
15:15 - 15:35 Dr. Min Liu 15:35 - 15:55 Jian Deng 15:55 - 16:15 Rongfei Nong |
| 16:15 - 16:45 | Poster and Discussion | Poster viewing, networking, and discussion |
| 16:45 - 17:00 | Awards and Closing |
Best paper awards, acknowledgements, closing remarks, and group photo |
Invited Speakers
Kostas Daniilidis
University of Pennsylvania, USA
Multi-view geometry, 3D scene reconstruction, and geometric vision theory.
Guillermo Gallego
Technical University of Berlin, Germany
Event-based vision, continuous-time motion estimation, and spatiotemporal modeling.
Priyadarshini Panda
University of Southern California, USA
Neuromorphic computing, spiking neural networks, and event-driven learning systems.
Shintaro Shiba
The University of Tokyo, Japan
Event-based perception for autonomous driving and large-scale real-world deployment.
Federico Becattini
University of Siena, Italy
Computer vision, Autonomous driving, Trajectory prediction, Fashion recommendation, Event camera
Daniel Gehrig
University of Pennsylvania, USA
Event-based optical flow, learning-based motion estimation, and high-speed vision.
Liyuan Pan
Beijing Institute of Technology, China
Event cameras, spiking vision models, and high-speed visual perception.
Bo Mu
OmniVision Technologies, Inc., USA
Event-based vision applications, neuromorphic sensors, and real-world deployment.
Min Liu
DVSense Technology Co., Ltd., China
Event camera sensors, imaging hardware design, and industrial vision systems.
Jian Deng
AlpsenTek, Switzerland
Neuromorphic vision sensors, edge imaging devices, and low-power perception hardware.
Rongfei Nong
Forma AI, Xingtai Qiyuan Technology Co., Ltd., China
Brain-inspired embodied AI, multimodal world model, and event-based perception.
Organizers
Hanyu Zhou
National University of Singapore
Yunfan Lu
Hong Kong University of Science and Technology (Guangzhou)
Shaoyu Liu
Xidian University
Haoyue Liu
Huazhong University of Science and Technology
Peiqi Duan
Peking University
Shihan Peng
Huazhong University of Science and Technology
Yinqiang Zheng
University of Tokyo
Boxin Shi
Peking University
Kuk-Jin Yoon
Korea Advanced Institute of Science and Technology
Hui Xiong
Hong Kong University of Science and Technology (Guangzhou)
Gim Hee Lee
National University of Singapore
Davide Scaramuzza
University of Zurich