Mesh-Aligned 3D Gaussian Splatting for Multi-Resolution Anti-Aliasing Rendering
IEEE Transactions on Circuits and Systems for Video Technology · 2025-08 · 35 (8) · 7368-7379
DOI: 10.1109/tcsvt.2025.3544760 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-08. Verfasst von Jiaming Liu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: SJTU Star Medical-Engineering Interdisciplinary Research Fund Key Project, SJTU Shenlan Program Key Project.
Abstract (Originalsprache)
3D Gaussian splatting (3DGS) suggests the use of explicit point-based 3D representations for high-fidelity novel view synthesis, with training and rendering speeds that are better than prior neural radiance fields. However, 3DGS relies heavily on synthetic point clouds generated by structure from motion (SfM) or multi view stereo (MVS) techniques, and lacks a well-defined method to initially condition them. In this work, we first propose a mesh-aligned method that attaches the 3D Gaussian to the extracted surface meshes for reliable initialization during training, and then directly manipulates the learnable 3DGS in the local coordinate using the triangular meshes. In addition, to constrain the stereo Gaussian on a planar mesh for better rendering, both normal and depth losses are designed to optimize the orientation and significance of the Gaussian. In practice, we further apply this method to multi-resolution scene rendering while resolving the aliasing effect. Unlike directly changing the size and number of Gaussians that may interfere the rendering quality at different resolutions, we argue that the properties of the modelled mesh are naturally resistant to aliasing effects. By utilising triangular meshes for Gaussian binding and adaptive learning, the proposed method can maintain high-fidelity rendering after splatting on multi-resolution concrete images. Extensive experiments demonstrate the effectiveness of our approach and its advantages over single full-resolution baseline.
Förderung
- SJTU Star Medical-Engineering Interdisciplinary Research Fund Key Project
- SJTU Shenlan Program Key Project
Zitieren
APA
Liu, J., Kong, L., Yan, J., & Chen, G. (2025). Mesh-Aligned 3D Gaussian Splatting for Multi-Resolution Anti-Aliasing Rendering. IEEE Transactions on Circuits and Systems for Video Technology, 35(8), 7368-7379. https://doi.org/10.1109/tcsvt.2025.3544760
Vancouver
Liu J, Kong L, Yan J, Chen G. Mesh-Aligned 3D Gaussian Splatting for Multi-Resolution Anti-Aliasing Rendering. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(8):7368-7379. doi:10.1109/tcsvt.2025.3544760
BibTeX
@article{Liu2025,
author = {Liu, Jiaming and Kong, Linghe and Yan, Jiajie and Chen, Guihai},
title = {Mesh-Aligned 3D Gaussian Splatting for Multi-Resolution Anti-Aliasing Rendering},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2025},
volume = {35},
number = {8},
pages = {7368--7379},
doi = {10.1109/tcsvt.2025.3544760}
}
EUVIMED