EUVIMEDEUVIMED entdecken
Crossref

Efficient Arbitrary-Scale Super-Resolution With Compact Gaussian Splatting

Jingyi Zhang, Haonan Jiang, Jiajun Dong, Shuai Shen, Yansong Tang, Lei Chen, Jiwen Lu

IEEE Transactions on Circuits and Systems for Video Technology · 2026-07 · 36 (7) · 10276-10290

DOI: 10.1109/tcsvt.2026.3675508 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-07. Verfasst von Jingyi Zhang und 6 weiteren Autor:innen. Die Arbeit nennt 62 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Arbitrary-scale super-resolution is an essential image upsampling task, typically tackled with implicit neural representations. Unlike INR-based methods that rely on slow per-pixel decoding, Gaussian Splatting is promising for arbitrary-scale super-resolution when the explicit region-based nature of GS allows for highly efficient rendering via a lightweight decoder. Recently, Gaussian splatting has outperformed implicit neural methods in 3D scenes. However, existing attempts to address the super-resolution problem with Gaussian splatting face efficiency and accuracy challenges, such as redundant Gaussian primitives and discrete pixel sampling. Efficient Gaussian applications may result in continuous texture constraints due to limited feature richness in explicit fields, particularly the mismatch between the learned Gaussian fields and out-of-distribution sampling rates. Moreover, insufficient discrete sampling based on the given upscale factor may fail to accurately represent the splatted Gaussian field in screen space, causing high-frequency signal redundancy and aliasing. To address these challenges, we propose a compact Gaussian splatting method for efficient arbitrary-scale super-resolution, CGSSR. It constructs an efficient Gaussian space by distilling the image into a reduced number of primitives, each represented by a compact, low-dimensional feature embedding. To balance detail preservation and anti-aliasing, we introduce a scale-aware smoothing filter to regulate splatting frequency. Extensive experiments show that CGSSR achieves superior performance over existing Gaussian-based methods, especially at large scales, with higher efficiency.

Förderung

  • National Natural Science Foundation of China
  • Beijing Natural Science Foundation

Zitieren

APA

Zhang, J., Jiang, H., Dong, J., Shen, S., Tang, Y., Chen, L., & Lu, J. (2026). Efficient Arbitrary-Scale Super-Resolution With Compact Gaussian Splatting. IEEE Transactions on Circuits and Systems for Video Technology, 36(7), 10276-10290. https://doi.org/10.1109/tcsvt.2026.3675508

Vancouver

Zhang J, Jiang H, Dong J, Shen S, Tang Y, Chen L, et al. Efficient Arbitrary-Scale Super-Resolution With Compact Gaussian Splatting. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(7):10276-10290. doi:10.1109/tcsvt.2026.3675508

BibTeX
@article{Zhang2026,
  author = {Zhang, Jingyi and Jiang, Haonan and Dong, Jiajun and Shen, Shuai and Tang, Yansong and Chen, Lei and Lu, Jiwen},
  title = {Efficient Arbitrary-Scale Super-Resolution With Compact Gaussian Splatting},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2026},
  volume = {36},
  number = {7},
  pages = {10276--10290},
  doi = {10.1109/tcsvt.2026.3675508}
}
Kostenlos starten →