SKU-Patch: Towards Efficient Instance Segmentation for Unseen Objects in Auto-Store
This addresses the need for efficient robotic bin picking in large-scale storehouses by reducing the tedious manual effort required for each new object, though it is incremental as it builds on existing instance segmentation methods.
The paper tackles the problem of instance segmentation for unseen objects in auto-store environments by introducing SKU-Patch, a patch-guided method that uses only a few image patches per new SKU to predict masks without manual annotation or model re-training, achieving state-of-the-art performance on benchmarks and nearly 100% grasping success rate on over 50 unseen SKUs.
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.