EUVIMEDEUVIMED entdecken
Crossref

RGB-D Data Compression via Bi-Directional Cross-Modal Prior Transfer and Enhanced Entropy Modeling

Yuyu Xu, Pingping Zhang, Minghui Chen, Qiudan Zhang, Wenhui Wu, Yun Zhang, Xu Wang

ACM Transactions on Multimedia Computing, Communications, and Applications · 28.02.2025 · 21 (2) · 1-17

DOI: 10.1145/3702997 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 25.12.2024. Verfasst von Yuyu Xu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Basic and Applied Basic Research Foundation, Stable Support Project of Shenzhen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

RGB-D data, being homogeneous cross-modal data, demonstrates significant correlations among data elements. However, current research focuses only on a uni-directional pattern of cross-modal contextual information, neglecting the exploration of bi-directional relationships in the compression field. Thus, we propose a joint RGB-D compression scheme, which is combined with Bi-Directional Cross-Modal Prior Transfer (Bi-CPT) modules and a Bi-Directional Cross-Modal Enhanced Entropy (Bi-CEE) model. The Bi-CPT module is designed for compact representations of cross-modal features, effectively eliminating spatial and modality redundancies at different granularity levels. In contrast to the traditional entropy models, our proposed Bi-CEE model not only achieves spatial-channel contextual adaptation through partitioning RGB and depth features but also incorporates information from other modalities as prior to enhance the accuracy of probability estimation for latent variables. Furthermore, this model enables parallel multi-stage processing to accelerate coding. Experimental results demonstrate the superiority of our proposed framework over the current compression scheme, outperforming both rate-distortion performance and downstream tasks, including surface reconstruction and semantic segmentation. The source code will be available at https://github.com/xyy7/Learning-based-RGB-D-Image-Compression .

Förderung

  • National Natural Science Foundation of China
  • Guangdong Basic and Applied Basic Research Foundation
  • Stable Support Project of Shenzhen

Zitieren

APA

Xu, Y., Zhang, P., Chen, M., Zhang, Q., Wu, W., Zhang, Y., & Wang, X. (2025). RGB-D Data Compression via Bi-Directional Cross-Modal Prior Transfer and Enhanced Entropy Modeling. ACM Transactions on Multimedia Computing, Communications, and Applications, 21(2), 1-17. https://doi.org/10.1145/3702997

Vancouver

Xu Y, Zhang P, Chen M, Zhang Q, Wu W, Zhang Y, et al. RGB-D Data Compression via Bi-Directional Cross-Modal Prior Transfer and Enhanced Entropy Modeling. ACM Transactions on Multimedia Computing, Communications, and Applications. 2025;21(2):1-17. doi:10.1145/3702997

BibTeX
@article{Xu2025,
  author = {Xu, Yuyu and Zhang, Pingping and Chen, Minghui and Zhang, Qiudan and Wu, Wenhui and Zhang, Yun and Wang, Xu},
  title = {RGB-D Data Compression via Bi-Directional Cross-Modal Prior Transfer and Enhanced Entropy Modeling},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2025},
  volume = {21},
  number = {2},
  pages = {1--17},
  doi = {10.1145/3702997}
}
Kostenlos starten →