用视觉变压器实现机器人抓取中的完整物体分割，恢复被遮挡部分。
ViTA-Seg: Vision Transformer for Amodal Segmentation in Robotics
- 基于全局注意力机制的ViT框架，可预测完整物体掩码。
- 双头结构在两个基准上达到高精度，推理速度满足实时需求。
- 专为工业抓取设计的合成数据集，提升模型泛化能力。
机器人抓取中物体遮挡会影响精准可靠的抓取规划。本文提出ViTA-Seg，一种无需类别信息的视觉变压器框架，通过全局注意力机制恢复完整物体掩码（包括隐藏区域），支持实时运行。设计两种架构：a）单头用于预测非视域掩码；b）双头同时输出非视域与遮挡掩码。构建了专为工业料箱抓取场景定制的逼真合成数据集ViTA-SimData。在两个非视域分割基准COOCA和KINS上的大量实验表明，ViTA-Seg双头结构在分割精度和计算效率上表现优异，实现了鲁棒的实时机器人操作。
原文摘要 · Abstract (English)
Occlusions in robotic bin picking compromise accurate and reliable grasp planning. We present ViTA-Seg, a class-agnostic Vision Transformer framework for real-time amodal segmentation that leverages global attention to recover complete object masks, including hidden regions. We proposte two architectures: a) Single-Head for amodal mask prediction; b) Dual-Head for amodal and occluded mask prediction. We also introduce ViTA-SimData, a photo-realistic synthetic dataset tailored to industrial bin-picking scenario. Extensive experiments on two amodal benchmarks, COOCA and KINS, demonstrate that ViTA-Seg Dual Head achieves strong amodal and occlusion segmentation accuracy with computational efficiency, enabling robust, real-time robotic manipulation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。