EUVIMEDEUVIMED entdecken
Crossref

GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution

Jintong Hu, Bin Xia, Bin Chen, Wenming Yang, Lei Zhang

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (4) · 3554-3562

DOI: 10.1609/aaai.v39i4.32369 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Jintong Hu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 36-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Implicit neural representations (INRs) have revolutionized arbitrary-scale super-resolution (ASSR) by modeling images as continuous functions. Most existing INR-based ASSR networks first extract features from the given low-resolution image using an encoder, and then render the super-resolved result via a multi-layer perceptron decoder. Although these approaches have shown promising results, their performance is constrained by the limited representation ability of discrete latent codes in the encoded features. In this paper, we propose a novel ASSR method named GaussianSR that overcomes this limitation through 2D Gaussian Splatting (2DGS). Unlike traditional methods that treat pixels as discrete points, GaussianSR represents each pixel as a continuous Gaussian field. The encoded features are simultaneously refined and upsampled by rendering the mutually stacked Gaussian fields. As a result, long-range dependencies are established to enhance representation ability. In addition, a classifier is developed to dynamically assign Gaussian kernels to all pixels to further improve flexibility. All components of GaussianSR (i.e. encoder, classifier, Gaussian kernels, and decoder) are jointly learned end-to-end. Experiments demonstrate that GaussianSR achieves superior ASSR performance with fewer parameters than existing methods while enjoying interpretable and content-aware feature aggregations.

Zitieren

APA

Hu, J., Xia, B., Chen, B., Yang, W., & Zhang, L. (2025). GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution. Proceedings of the AAAI Conference on Artificial Intelligence, 39(4), 3554-3562. https://doi.org/10.1609/aaai.v39i4.32369

Vancouver

Hu J, Xia B, Chen B, Yang W, Zhang L. GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(4):3554-3562. doi:10.1609/aaai.v39i4.32369

BibTeX
@article{Hu2025,
  author = {Hu, Jintong and Xia, Bin and Chen, Bin and Yang, Wenming and Zhang, Lei},
  title = {GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {4},
  pages = {3554--3562},
  doi = {10.1609/aaai.v39i4.32369}
}
Kostenlos starten →