Print Email Facebook Twitter Push-the-Boundary Title Push-the-Boundary: Boundary-Aware Feature Propagation for Semantic Segmentation of 3D Point Clouds Author Du, S. (TU Delft Urban Data Science) Ibrahimli, N. (TU Delft Urban Data Science) Stoter, J.E. (TU Delft Urban Data Science) Kooij, J.F.P. (TU Delft Intelligent Vehicles) Nan, L. (TU Delft Urban Data Science) Contributor Ceballos, Cristina (editor) Date 2022 Abstract Feedforward fully convolutional neural networks currently dominate in semantic segmentation of 3D point clouds. Despite their great success, they suffer from the loss of local information at low-level layers, posing significant challenges to accurate scene segmentation and precise object boundary delineation. Prior works either address this issue by post-processing or jointly learn object boundaries to implicitly improve feature encoding of the networks. These approaches often require additional modules which are difficult to integrate into the original architecture. To improve the segmentation near object boundaries, we propose a boundary-aware feature propagation mechanism. This mechanism is achieved by exploiting a multitask learning framework that aims to explicitly guide the boundaries to their original locations. With one shared encoder, our network outputs (i) boundary localization, (ii) prediction of directions pointing to the object's interior, and (iii) semantic segmentation, in three parallel streams. The predicted boundaries and directions are fused to propagate the learned features to refine the segmentation. We conduct extensive experiments on the S3DIS and SensatUrban datasets against various baseline methods, demonstrating that our proposed approach yields consistent improvements by reducing boundary errors. Our code is available at https://github.com/shenglandu/PushBoundary. Subject point cloud compressionlocation awarenessthree-dimensional displayssemantic segmentationsemanticsself-supervised learningencoding To reference this document use: http://resolver.tudelft.nl/uuid:18f3be6d-76da-4bc2-9740-a1f3a0105274 DOI https://doi.org/10.1109/3DV57658.2022.00025 Publisher IEEE, Prague Embargo date 2023-09-22 ISBN 978-1-6654-5670-8 Source Proceedings - 2022 International Conference on 3D Vision, 3DV 2022 Event 2022 International Conference on 3D Vision (3DV), 2022-09-12 → 2022-09-15, Czech Technical University, Prague, Czech Republic Bibliographical note This work was supported by the 3D Urban Understanding Lab funded by the TU Delft AI Initiative. Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type conference paper Rights © 2022 S. Du, N. Ibrahimli, J.E. Stoter, J.F.P. Kooij, L. Nan Files PDF Push-the-Boundary_Boundar ... Clouds.pdf 951.03 KB Close viewer /islandora/object/uuid:18f3be6d-76da-4bc2-9740-a1f3a0105274/datastream/OBJ/view