In this section
@inproceedings{Dong:2025:10.1109/icma65362.2025.11120697,
author = {Dong, W and Bhattacharya, D and Kobayashi, A and Seino, A and Tokuda, F and Huang, X and Tang, K and Tien, NC and Kosuge, K},
doi = {10.1109/icma65362.2025.11120697},
pages = {1343--1348},
publisher = {IEEE},
title = {Precise top-layer fabric segmentation for fabric destacking with edge- and shape-aware deep networks},
url = {http://dx.doi.org/10.1109/icma65362.2025.11120697},
year = {2025}
}
TY - CPAPER
AB - Fabric destacking requires precise segmentation of the topmost fabric layer, a task complicated by subtle fabric boundaries and high visual similarity between fabric layers. Existing semantic and edge-based segmentation approaches often struggle with these complexities, limiting the performance of robotic manipulation for different tasks. In this work, a novel segmentation training architecture tailored for top-layer fabric segmentation in stacked fabrics is proposed. The method ex-tends the classical encoder-decoder framework by introducing two specialized branches-an edge-aware branch and a shape-aware branch-that are used to supervise the backbone network for better tuning. The edge-aware branch enhances boundary delineation, while the shape-aware branch guides the network to capture and align the overall fabric shape with reference masks derived from Computer Aided Design (CAD) models. Experiments on a real-world fabric dataset demonstrate that the training approach outperforms established baselines, verifying the effectiveness of the multi-branch design through both quan-titative results and ablation studies.
AU - Dong,W
AU - Bhattacharya,D
AU - Kobayashi,A
AU - Seino,A
AU - Tokuda,F
AU - Huang,X
AU - Tang,K
AU - Tien,NC
AU - Kosuge,K
DO - 10.1109/icma65362.2025.11120697
EP - 1348
PB - IEEE
PY - 2025///
SP - 1343
TI - Precise top-layer fabric segmentation for fabric destacking with edge- and shape-aware deep networks
UR - http://dx.doi.org/10.1109/icma65362.2025.11120697
UR - https://doi.org/10.1109/icma65362.2025.11120697
ER -