发表机构
Hong Kong University of Science and Technology (Guangzhou); National University of Singapore; Xidian University; Tsinghua University; Huazhong University of Science and Technology; Peking University; The University of Tokyo; University of Zurich（香港科技大学（广州）; 新加坡国立大学; 西安电子科技大学; 清华大学; 华中科技大学; 北京大学; 东京大学; 苏黎世大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对宽光照范围的事件引导恢复，SEE Challenge 2026基于SEE-600K数据集组织竞赛，采用开放系统协议，以PSNR排名、SSIM为辅，验证了六种系统并分析了其性能与失败模式。
AI 中文摘要
事件相机提供高动态范围，并在传统RGB帧可能噪声或饱和的光照条件下保留亮度变化线索。为了在宽光照范围内对事件引导的恢复进行基准测试，我们在ECCV 2026的事件基多模态视觉研讨会上组织了SEE Challenge 2026。该任务基于一个或多个RGB帧、同步事件以及组织者提供的标量目标亮度统计量进行恢复。它使用SEE-600K数据集，该数据集包含来自202个真实世界场景的610,126个图像-事件观测，涵盖低光、正常光和高光条件，光照变化高达1000倍。挑战采用开放系统协议：参与者可以使用不同的时间上下文、架构、预训练权重、测试时增强和后处理策略。PSNR决定排名，SSIM作为次要指标报告。约70支团队注册了兴趣，收到15个有效的CodaBench提交。六个不同的团队完成了组织者方的身份和技术验证，提供了方法描述、检查点、推理代码和说明，并被纳入此处报告的已验证开放系统排名。除了排名，本报告还分析了曝光子集、语义上不同的测试案例、一个共同的失败模式、系统设计选择和推理策略。顶级系统获得紧密间隔的平均分数，而最佳方法因案例和指标而异；在严重欠曝光下，所有已验证系统都保留可见的局部错误。
英文摘要
Event cameras provide a high dynamic range and preserve brightness-change cues in lighting conditions where conventional RGB frames may be noisy or saturated. To benchmark event-guided restoration across a broad illumination range, we organized the SEE Challenge 2026 with the Event-Based Multimodal Vision Workshop at ECCV 2026. The task conditions restoration on one or more RGB frames, synchronized events, and a scalar target-brightness statistic provided by the organizers. It uses SEE-600K, which contains 610,126 image-event observations from 202 real-world scenes spanning low-light, normal-light, and high-light conditions with illumination variations of up to 1,000$\times$. The challenge follows an open-system protocol: participants may use different temporal contexts, architectures, pretrained weights, test-time augmentation, and post-processing strategies. PSNR determines the ranking, and SSIM is reported as a secondary metric. Around 70 teams registered interest and 15 valid CodaBench submissions were received. Six distinct teams completed organizer-side identity and technical verification, provided method descriptions, checkpoints, inference code, and instructions, and are included in the verified open-system ranking reported here. Beyond the ranking, this report analyzes exposure subsets, semantically distinct test cases, a shared failure pattern, system design choices, and inference strategies. The top systems obtain closely spaced average scores, while the best-performing method varies across cases and metrics; under severe underexposure, all verified systems retain visible local errors.
CommentsThis report has been accepted for publication at an ECCV 2026 Workshop
