JSCC-Aided INR for High-Frequency Detail Preservation in LiDAR

Kuwabara, Akihiro; Kato, Sorachi; Koike-Akino, Toshiaki; Fujihashi, Takuya

doi:https://doi.org/10.1109/OJCOMS.2025.3594545

JSCC-Aided INR for High-Frequency Detail Preservation in LiDAR

Kuwabara, Akihiro; Kato, Sorachi; Koike-Akino, Toshiaki et al.

IEEE Open Journal of the Communications Society, 2025, 6, 6352-6367

アクセス数:70件（2026-02-15 20:21 集計）

固定URL: https://hdl.handle.net/11094/102939

閲覧可能ファイル

ファイル	フォーマット	利用条件	サイズ	閲覧回数	利用開始日	説明	information
IEEEopenJCommunSoc_6_6352	pdf	なし	7.36 MB	42	2025.10.31

Creative Commons : 表示

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

タイトル	JSCC-Aided INR for High-Frequency Detail Preservation in LiDAR
著者	著者名 Kuwabara, Akihiro
	ORCID 0000-0002-6896-5293 0000-0002-6896-5293 Scopus Author ID 57221140740 57221140740 著者名 Kato, Sorachi
	著者名 Koike-Akino, Toshiaki
	NRID 1000010785520 1000010785520 ORCID 0000-0002-6960-0122 0000-0002-6960-0122 researchmap permalink T-Fujihashi T-Fujihashi Scopus Author ID 55440476600 55440476600 著者名 Fujihashi, Takuya
キーワード等	implicit neural representation
	joint source-channel coding
	LiDAR
	point clouds
	pseudo-analog transmission
内容	Kuwabara A., Kato S., Koike-Akino T., et al. JSCC-Aided INR for High-Frequency Detail Preservation in LiDAR. IEEE Open Journal of the Communications Society 6, 6352 (2025); https://doi.org/10.1109/OJCOMS.2025.3594545.
抄録	Light Detection and Ranging (LiDAR) sensors generate accurate 3D representations of real-world environments, which are essential for applications of 3D scene understanding. However, the substantial volume of LiDAR data poses significant challenges for efficient compression and transmission. Implicit neural representation (INR) has gained attention for its compact data representation, but its capacity to accurately represent high-frequency details is insufficient when using small models. In this paper, we propose a novel joint source-channel coding (JSCC) scheme that integrates INR with analog residual transmission for high-quality and efficient point cloud transmission. This scheme is designed to compensate for the limited high-frequency representation of INRs by transmitting the unmodeled details as residuals via pseudo-analog modulation. This integrated approach enables continuous reconstruction quality adaptation to varying wireless channel conditions and effectively mitigates the stair-case effect inherent in conventional digital schemes. Evaluations on the KITTI dataset demonstrate that the proposed scheme outperforms conventional and INR-based compression methods in terms of R-D performance and detection quality at low bitrates.
出版者	Institute of Electrical and Electronics Engineers Inc.
収録物名	IEEE Open Journal of the Communications Society
巻(号)	6
ページ	6352-6367
刊行年月	2025-07-31
言語	英語
ハンドルURL	https://hdl.handle.net/11094/102939
eISSN	2644125X
関連情報 (isIdenticalTo)	DOI (出版社版) https://doi.org/10.1109/OJCOMS.2025.3594545
アクセス権	open access
権利情報	This article is licensed under a Creative Commons Attribution 4.0 International License.
出版タイプ	Version of Record
カテゴリ	学術雑誌論文 Journal Article

資源タイプ	学術雑誌論文
ローカル資源タイプ	学術雑誌論文
DCMI資源タイプ	text
DCTERMS.bibliographicCitation	IEEE Open Journal of the Communications Society. 2025, 6, p. 6352-6367
DC.title	JSCC-Aided INR for High-Frequency Detail Preservation in LiDAR
DC.creator	Kuwabara, Akihiro
	Kato, Sorachi
	Koike-Akino, Toshiaki
	Fujihashi, Takuya
DC.publisher	Institute of Electrical and Electronics Engineers Inc.
DC.language' scheme='DCTERMS.RFC1766	英語
DC.type' scheme='DCTERMS.DCMIType	text
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2025-07-31
DC.identifier	https://doi.org/10.1109/OJCOMS.2025.3594545
DC.subject	implicit neural representation
	joint source-channel coding
	LiDAR
	point clouds
	pseudo-analog transmission
DC.description	Kuwabara A., Kato S., Koike-Akino T., et al. JSCC-Aided INR for High-Frequency Detail Preservation in LiDAR. IEEE Open Journal of the Communications Society 6, 6352 (2025); https://doi.org/10.1109/OJCOMS.2025.3594545.
DCTERMS.abstract	Light Detection and Ranging (LiDAR) sensors generate accurate 3D representations of real-world environments, which are essential for applications of 3D scene understanding. However, the substantial volume of LiDAR data poses significant challenges for efficient compression and transmission. Implicit neural representation (INR) has gained attention for its compact data representation, but its capacity to accurately represent high-frequency details is insufficient when using small models. In this paper, we propose a novel joint source-channel coding (JSCC) scheme that integrates INR with analog residual transmission for high-quality and efficient point cloud transmission. This scheme is designed to compensate for the limited high-frequency representation of INRs by transmitting the unmodeled details as residuals via pseudo-analog modulation. This integrated approach enables continuous reconstruction quality adaptation to varying wireless channel conditions and effectively mitigates the stair-case effect inherent in conventional digital schemes. Evaluations on the KITTI dataset demonstrate that the proposed scheme outperforms conventional and INR-based compression methods in terms of R-D performance and detection quality at low bitrates.
DC.rights	This article is licensed under a Creative Commons Attribution 4.0 International License.
DC.format	102939
citation_title	JSCC-Aided INR for High-Frequency Detail Preservation in LiDAR
citation_author	Kuwabara, Akihiro
	Kato, Sorachi
	Koike-Akino, Toshiaki
	Fujihashi, Takuya
citation_publisher	Institute of Electrical and Electronics Engineers Inc.
citation_language	英語
citation_date	2025-07-31
citation_journal_title	IEEE Open Journal of the Communications Society
citation_volume	6
citation_firstpage	6352
citation_lastpage	6367
citation_doi	https://doi.org/10.1109/OJCOMS.2025.3594545
citation_public_url	https://hdl.handle.net/11094/102939

JSCC-Aided INR for High-Frequency Detail Preservation in LiDAR

閲覧可能ファイル

論文情報

論文詳細を表示