Memory-Augmented Re-Completion for 3D Semantic Scene Completion
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (7) · 7446-7454
DOI: 10.1609/aaai.v39i7.32801 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Yu-Wen Tseng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
Semantic Scene Completion (SSC) aims to reconstruct a 3D voxel representation occupied by semantic classes based on ordinary inputs such as 2D RGB images, depth maps, or point clouds. Given the cost-effective and promising applications in autonomous driving, camera-based SSC has attracted considerable attention to developing various approaches. However, current methods mainly focus on precise 2D-to-3D projection while overlooking the challenge of completing invisible regions, leading to numerous false negatives and suboptimal SSC performance. To address this issue, we propose a novel architecture, Memory-augmented Re-completion (MARE), designed to enhance completion capability. Our MARE model encapsulates regional relationships by incorporating a memory bank that stores vital region-tokens while two protocols concerning diversity and age are adopted to optimize the bank adversarially. Additionally, we introduce a Re-completion pipeline incorporated with an Information Spreading module to progressively complete the invisible regions while bridging the scale gap between region-level and voxel-level information. Extensive experiments conducted on the SSCBench-KITTI-360 and SemanticKITTI datasets validate the effectiveness of our approach.
Zitieren
APA
Tseng, Y., Yang, S., Wu, J., Liao, I., Li, Y., Shuai, H., & Cheng, W. (2025). Memory-Augmented Re-Completion for 3D Semantic Scene Completion. Proceedings of the AAAI Conference on Artificial Intelligence, 39(7), 7446-7454. https://doi.org/10.1609/aaai.v39i7.32801
Vancouver
Tseng Y, Yang S, Wu J, Liao I, Li Y, Shuai H, et al. Memory-Augmented Re-Completion for 3D Semantic Scene Completion. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(7):7446-7454. doi:10.1609/aaai.v39i7.32801
BibTeX
@article{Tseng2025,
author = {Tseng, Yu-Wen and Yang, Sheng-Ping and Wu, Jhih-Ciang and Liao, I-Bin and Li, Yung-Hui and Shuai, Hong-Han and Cheng, Wen-Huang},
title = {Memory-Augmented Re-Completion for 3D Semantic Scene Completion},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {7},
pages = {7446--7454},
doi = {10.1609/aaai.v39i7.32801}
}
EUVIMED