In large-scale storehouses, precise instance masks are crucial for robotic
bin picking but are challenging to obtain. Existing instance segmentation
methods typically rely on a tedious process of scene collection, mask
annotation, and network fine-tuning for every single Stock Keeping Unit (SKU).
This paper presents SKU-Patch, a new patch-guided instance segmentation
solution, leveraging only a few image patches for each incoming new SKU to
predict accurate and robust masks, without tedious manual effort and model
re-training. Technical-wise, we design a novel transformer-based network with
(i) a patch-image correlation encoder to capture multi-level image features
calibrated by patch information and (ii) a patch-aware transformer decoder with
parallel task heads to generate instance masks. Extensive experiments on four
storehouse benchmarks manifest that SKU-Patch is able to achieve the best
performance over the state-of-the-art methods. Also, SKU-Patch yields an
average of nearly 100% grasping success rate on more than 50 unseen SKUs in a
robot-aided auto-store logistic pipeline, showing its effectiveness and
practicality.

在大规模仓库中，对于机器人的货箱拾取来说，精确的实例掩模至关重要，但往往很难获得。本文提出了一种新的基于补丁引导的实例分割解决方案 SKU-Patch，利用每个新的 SKU 仅需少量图像补丁来预测准确和稳健的掩模，避免了繁琐的手动操作和模型重训练。技术上，我们设计了一种新颖的基于 Transformer 的网络，具备（i）用于捕捉由补丁信息校准的多层次图像特征的图像补丁 - 图像相关编码器和（ii）带有并行任务头的补丁感知 Transformer 解码器，用于生成实例掩模。在四个仓库基准测试上进行的大量实验证明 SKU-Patch 能够在性能上超过现有最先进的方法。此外，SKU-Patch 在机器人辅助的自动货运管道中对 50 多个未见过的 SKU 的平均抓取成功率接近 100％，显示出其有效性和实用性。