EUVIMEDEUVIMED entdecken
Crossref

SSC-VAE: Structured Sparse Coding Based Variational Autoencoder for Detail Preserved Image Reconstruction

Hao Wang, Lu Wang, Zhongyu Wang, Lixin Ma, Ye Luo

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (7) · 7665-7673

DOI: 10.1609/aaai.v39i7.32825 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Hao Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Discrete latent representation techniques, such as Vector Quantization (VQ) and Sparse Coding (SC), have demonstrated superior image reconstruction and generation quality compared to continuous representation methods in Variational Autoencoders (VAEs). However, existing approaches often treat the latent representations of an image independently in their discrete representation space, neglecting both the inherent structural information within each representation and the correlations among them. This oversight leads to coarse representations and suboptimal generated results. In this paper, we address these limitations by introducing correlations among and within the latent representations of individual images in the latent discrete space of VAEs using sparse coding. We impose two-dimensional structural information through adaptive thresholding, enhancing local structure in image representations while suppressing noise via parsimonious representation with a learned dictionary. Empirical studies on three real benchmark datasets, including a clinical Ultrasound dataset, BSDS500, and mini-Imagenet, demonstrate that our proposed model preserves fine-grained details in image reconstruction and significantly outperforms baseline models of SC-VAE and VQ-VAE across objective and subjective image quality metrics. Particularly noteworthy are the substantial performance improvements observed on the ultrasound dataset, where structure information is crucial. Specifically, we observe significant performance improvements of 7.68 % and 17.03 % in SSIM, 3.25 dB and 6.58 dB in PSNR, 0.15 and 0.24 in LPIPS, 45.38 and 84.05 in FID over SC-VAE and VQ-VAE, respectively, indicating the superiority of our method in terms of image reconstruction quality and fidelity.

Zitieren

APA

Wang, H., Wang, L., Wang, Z., Ma, L., & Luo, Y. (2025). SSC-VAE: Structured Sparse Coding Based Variational Autoencoder for Detail Preserved Image Reconstruction. Proceedings of the AAAI Conference on Artificial Intelligence, 39(7), 7665-7673. https://doi.org/10.1609/aaai.v39i7.32825

Vancouver

Wang H, Wang L, Wang Z, Ma L, Luo Y. SSC-VAE: Structured Sparse Coding Based Variational Autoencoder for Detail Preserved Image Reconstruction. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(7):7665-7673. doi:10.1609/aaai.v39i7.32825

BibTeX
@article{Wang2025,
  author = {Wang, Hao and Wang, Lu and Wang, Zhongyu and Ma, Lixin and Luo, Ye},
  title = {SSC-VAE: Structured Sparse Coding Based Variational Autoencoder for Detail Preserved Image Reconstruction},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {7},
  pages = {7665--7673},
  doi = {10.1609/aaai.v39i7.32825}
}
Kostenlos starten →