基于异步事件的图混合神经网络全景分割
Asynchronous Events-based Panoptic Segmentation using Graph Mixer Neural Network
AI总结：
针对机器人抓取动态场景下物体分割的难题，提出带协同上下文混合层的图混合神经网络处理异步事件3D图，在ESD数据集上的交并比与像素精度均优于现有最优方法。
摘要：
在机器人抓取场景下，当面临实时运行、遮挡、低光照、运动模糊以及物体尺寸多变等动态条件时，物体分割会遇到诸多困难。针对这些挑战，我们提出了图混合神经网络（Graph Mixer Neural Network），该网络包含一种新型的协同上下文混合层，应用于基于异步事件构建的3D事件图上。所提出的混合层旨在并行地在四个最近邻层级上传播事件图内的时空相关性。我们在Event-based Segmentation（ESD，基于事件的分割）数据集上评估了所提方法的有效性，该数据集包含五种独特的图像退化挑战：遮挡、模糊、亮度、轨迹、尺度变化，还包含已知与未知物体的分割任务。结果表明，我们提出的方法在平均交并比和像素精度方面均优于现有最优方法。代码可在https://github.com/sanket0707/GNN-Mixer.git获取。
英文摘要：
In the context of robotic grasping, object segmentation encounters several difficulties when faced with dynamic conditions such as real-time operation, occlusion, low lighting, motion blur, and object size variability. In response to these challenges, we propose the Graph Mixer Neural Network that includes a novel collaborative contextual mixing layer, applied to 3D event graphs formed on asynchronous events. The proposed layer is designed to spread spatiotemporal correlation within an event graph at four nearest neighbor levels parallelly. We evaluate the effectiveness of our proposed method on the Event-based Segmentation (ESD) Dataset, which includes five unique image degradation challenges, including occlusion, blur, brightness, trajectory, scale variance, and segmentation of known and unknown objects. The results show that our proposed approach outperforms state-of-the-art methods in terms of mean intersection over the union and pixel accuracy. Code available at: https://github.com/sanket0707/GNN-Mixer.git
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
