发表机构
University of Chile; Advanced Mining Technology Center (AMTC), University of Chile; The Iniciativa de Datos e Inteligencia Artificial, University of Chile（智利大学; 智利大学先进采矿技术中心; 智利大学数据与人工智能计划）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该文提出多模态数据库Moving6DPoSe，含真实与合成子集，提供16个物体、1702个rosbag及分割、检测、6D姿态标注，实验显示事件式表示在运动物体分割上更鲁棒。
AI 中文摘要
由于运动模糊和传统帧式相机有限的时间分辨率，估计运动物体的6D姿态仍然具有挑战性。现有的事件相机数据集进一步提供了有限的传感模态、标注和运动场景。我们引入了Moving6DPoSe，一个多模态数据库，包含两个互补的子集：包含真实世界记录的Moving6DPoSe-R和由相同物体生成的合成序列的Moving6DPoSe-S。该数据集包含16个扫描物体和1,702个真实及合成的rosbag，涵盖多种运动场景，并带有语义分割、目标检测和单目6D姿态估计的标注。我们进一步提供了所有三个任务在帧式和事件式模态下的基线结果。实验结果表明，事件式表示在运动物体分割方面比传统RGB图像更鲁棒，而单目方向估计仍然具有挑战性，这凸显了Moving6DPoSe在运动物体感知研究中的潜力。
英文摘要
Estimating the 6D pose of moving objects remains challenging due to motion blur and the limited temporal resolution of conventional frame-based cameras. Existing event-based datasets further provide limited sensing modalities, annotations, and motion scenarios. We introduce Moving6DPoSe, a multimodal database comprising two complementary subsets: Moving6DPoSe-R with real-world recordings and Moving6DPoSe-S with synthetic sequences generated from the same objects. The dataset contains 16 scanned objects and 1,702 real and synthetic rosbags spanning multiple motion scenarios, with annotations for semantic segmentation, object detection, and monocular 6D pose estimation. We further provide baseline results for all three tasks across frame and event-based modalities. Experimental results show that event-based representations achieve more robust moving-object segmentation than conventional RGB images, while monocular orientation estimation remains challenging, highlighting the potential of Moving6DPoSe for moving-object perception research.
Journal refThe 19th European Conference on Computer Vision Workshops (ECCVW 2026); Workshop on Neuromorphic Vision (NeVi)
