EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Denoise-GS: Self-Supervised Denoising for Sparse-View 3D Gaussian Splatting

Yabo Xu iD, Jin Ding iD, Jianbin Zhang, Ping Tan iD, Mingrui Li

Sensors · 18.01.2026 · 26 (2) · 651

DOI: 10.3390/s26020651 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 18.01.2026. Verfasst von Yabo Xu und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Automation and Electrical Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, 2025 Open Project of the State Key Laboratory of Industrial Control 592 Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Three-dimensional Gaussian splatting has emerged as a mainstream method in the field of new viewpoint synthesis due to its outstanding performance. However, its generation quality typically degrades significantly when input viewpoints are sparse. The introduction of InstantSplat further improved new viewpoint generation in sparse viewpoint scenarios. Nevertheless, these methods produce suboptimal results in sparse viewpoint scenes with noise and no camera prior. To address this issue, we propose Denoise-GS, a two-round optimization framework combining N2V-UNet denoising with InstantSplat rendering. First, Noise2Void performs self-supervised denoising on the input image. Next, pose grouping is conducted based on InstantSplat rendered results. Finally, a second round of refinement is applied to the UNet through a joint loss function. The final denoised result is then re-rendered to achieve a higher-quality output image. To simulate a real noisy environment, we added Gaussian noise to the input images. Tests on multiple datasets show that, compared with other mainstream methods, our approach produces images with higher PSNR and SSIM. The method performs well in novel view generation when the input images are sparse and noisy, providing an innovative and practical solution for three-dimensional reconstruction.

Schlagwörter

Stichwörter der Autor:innen

3D Gaussian splattingdenoisesparse-view reconstructionview synthesisvolume rendering

Autor:innen und Institutionen

  • College of Automation and Electrical Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, China.
  • School of Information and Communication Engineering, Dalian University of Technology, Dalian 116085, China.

ORCID-Profile: Yabo Xu, Jin Ding, Ping Tan

Förderung

  • National Natural Science Foundation of China
  • 2025 Open Project of the State Key Laboratory of Industrial Control 592 Technology

Zitieren

APA

Xu, Y., Ding, J., Zhang, J., Tan, P., & Li, M. (2026). Denoise-GS: Self-Supervised Denoising for Sparse-View 3D Gaussian Splatting. Sensors, 26(2), 651. https://doi.org/10.3390/s26020651

Vancouver

Xu Y, Ding J, Zhang J, Tan P, Li M. Denoise-GS: Self-Supervised Denoising for Sparse-View 3D Gaussian Splatting. Sensors. 2026;26(2):651. doi:10.3390/s26020651

BibTeX
@article{Xu2026,
  author = {Xu, Yabo and Ding, Jin and Zhang, Jianbin and Tan, Ping and Li, Mingrui},
  title = {Denoise-GS: Self-Supervised Denoising for Sparse-View 3D Gaussian Splatting},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {2},
  pages = {651},
  doi = {10.3390/s26020651}
}
Kostenlos starten →