Journal article · 2026 · Open access

DepthGS: Depth-Guided Gaussian Splatting with Adaptive Regularization for High-Quality Surface Reconstruction

Xiao Ren, Yu Liu, Ning An, Jian Cheng, Xin Qiao, Youfu Li, He Kong

IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–12 · Published 1 January 2026 · DOI 10.1109/tpami.2026.3751295

Open full textCite this paper

In brief

“DepthGS: Depth-Guided Gaussian Splatting with Adaptive Regularization for High-Quality Surface Reconstruction” is a 2026 journal article by Xiao Ren and 6 co-authors, published in IEEE Transactions on Pattern Analysis and Machine Intelligence. OpenAlex counts 0 citations as of 16 November 2026. It is open access under a CC BY licence: the full text is free to read at IEEE Transactions on Pattern Analysis and Machine Intelligence.

Citations
0
References
2
Authors
7

Abstract

Recently, 3D Gaussian Splatting (3DGS) has emerged as an efficient representation for novel view synthesis, offering fast differentiable rendering and high visual fidelity, and has increasingly been extended to surface reconstruction. However, the relationship between depth information and reconstruction error remains insufficiently understood, limiting the principled design of geometric optimization strategies. To address this issue, we propose DepthGS, a depth-guided Gaussian splatting framework. We derive theoretical relations between depth discrepancies and reconstruction error under single-view and multi-view conditions. For single-view optimization, we propose a depth-difference-guided adaptive normal regularization strategy that modulates the normal constraint strength using a geometric reliability weight computed from local depth differences. For multi-view optimization, we introduce a cross-view depth consistency regularization strategy that enforces consistency between neighboring-view depth maps and the corresponding depth predictions transformed from the current view, thereby promoting multi-view geometric consistency. Extensive experiments on DTU, Mip-NeRF360, and Tanks and Temples demonstrate that DepthGS achieves competitive performance in both surface reconstruction and novel view synthesis.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Ren, X., Liu, Y., An, N., Cheng, J., Qiao, X., Li, Y., & Kong, H. (2026). DepthGS: Depth-Guided Gaussian Splatting with Adaptive Regularization for High-Quality Surface Reconstruction. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–12. https://doi.org/10.1109/tpami.2026.3751295

MLA 9

Ren, Xiao, et al. “DepthGS: Depth-Guided Gaussian Splatting with Adaptive Regularization for High-Quality Surface Reconstruction.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, 2026, pp. 1–12. https://doi.org/10.1109/tpami.2026.3751295.

Chicago

Ren, Xiao, Yu Liu, Ning An, Jian Cheng, Xin Qiao, Youfu Li, and He Kong. 2026. “DepthGS: Depth-Guided Gaussian Splatting with Adaptive Regularization for High-Quality Surface Reconstruction.” IEEE Transactions on Pattern Analysis and Machine Intelligence PP: 1–12. https://doi.org/10.1109/tpami.2026.3751295.

Harvard

Ren, X. et al. (2026) ‘DepthGS: Depth-Guided Gaussian Splatting with Adaptive Regularization for High-Quality Surface Reconstruction’, IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, pp. 1–12. doi:10.1109/tpami.2026.3751295.

IEEE

X. Ren et al., “DepthGS: Depth-Guided Gaussian Splatting with Adaptive Regularization for High-Quality Surface Reconstruction,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, pp. 1–12, 2026, doi: 10.1109/tpami.2026.3751295.

BibTeX

@article{ren2026depthgs,
  title     = {{DepthGS: Depth-Guided Gaussian Splatting with Adaptive Regularization for High-Quality Surface Reconstruction}},
  author    = {Ren, Xiao and Liu, Yu and An, Ning and Cheng, Jian and Qiao, Xin and Li, Youfu and Kong, He},
  journal   = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year      = {2026},
  volume    = {PP},
  pages     = {1--12},
  doi       = {10.1109/tpami.2026.3751295},
  url       = {https://doi.org/10.1109/tpami.2026.3751295}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › 3D Shape Modeling and Analysis

  • 3D Gaussian Splatting
  • novel view synthesis
  • geometry optimization
  • depth estimation

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Ren, X., Liu, Y., An, N., Cheng, J., Qiao, X., Li, Y., & Kong, H. (2026). DepthGS: Depth-Guided Gaussian Splatting with Adaptive Regularization for High-Quality Surface Reconstruction. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–12. https://doi.org/10.1109/tpami.2026.3751295

How many times has this paper been cited?

0 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at IEEE Transactions on Pattern Analysis and Machine Intelligence: sign in and open the full text from this page.

Who wrote this paper?

Xiao Ren, Yu Liu, Ning An, Jian Cheng, Xin Qiao, Youfu Li, He Kong.

What is the DOI of this paper?

10.1109/tpami.2026.3751295, permanently at https://doi.org/10.1109/tpami.2026.3751295. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.