3DGS-HPC: Distractor-free 3D Gaussian Splatting with hybrid patch-wise classification

Chen, Jiahao, Qin, Yipeng ORCID: https://orcid.org/0000-0002-1551-9126, Zhao, Ganlong, Li, Xin, Wang, Wenping and Li, Guanbin 2026. 3DGS-HPC: Distractor-free 3D Gaussian Splatting with hybrid patch-wise classification. Presented at: The Forty-Third International Conference on Machine Learning (ICML), Seoul, South Korea, 6-11 July 2026. Proceedings of the 43rd International Conference on Machine Learning. Item availability restricted.

	PDF - Accepted Post-Print Version Restricted to Repository staff only Download (18MB)
Preview	PDF (Provisional file) - Accepted Post-Print Version Download (17kB) | Preview

Abstract

3D Gaussian Splatting (3DGS) has demonstrated remarkable performance in novel view synthesis and 3D scene reconstruction, but its quality often degrades in real-world environments due to transient distractors, such as moving objects and varying shadows. Existing methods commonly introduce semantic priors from pre-trained vision models either to group pixels into coherent regions or to define perceptual error metrics. However, semantic grouping is often misaligned with the binary static/transient distinction, while perceptual features can be fragile under appearance perturbations introduced during 3DGS optimization. We propose 3DGS-HPC, a framework that addresses these issues by combining two complementary principles: a patch-wise classification strategy that leverages local spatial consistency for robust region-level decisions, and a hybrid classification metric that adaptively integrates photometric and perceptual cues for more reliable separation. Extensive experiments demonstrate the superiority and robustness of our method in mitigating distractors to improve 3DGS-based novel view synthesis. Our project page is https://cnhaox.github.io/3DGS-HPC/.

Item Type:	Conference or Workshop Item - published (Paper)
Status:	In Press
Schools:	Schools > Computer Science & Informatics
Date of First Compliant Deposit:	2 June 2026
Date of Acceptance:	30 April 2026
Last Modified:	05 Nov 2026 12:45
URI:	https://orca.cardiff.ac.uk/id/eprint/187247

Actions (repository staff only)

Edit Item