3DGS-HPC: Distractor-free 3D Gaussian Splatting with Hybrid Patch-wise Classification

TL;DR

This paper introduces 3DGS-HPC, a novel framework that enhances 3D Gaussian Splatting by effectively removing transient distractors using patch-wise classification and hybrid metrics, leading to improved view synthesis quality.

Contribution

The paper presents a new distractor removal method for 3D Gaussian Splatting that combines local spatial consistency with adaptive photometric and perceptual cues.

Findings

Significantly reduces distractor effects in 3DGS.

Improves novel view synthesis quality in real-world scenes.

Demonstrates robustness against appearance perturbations.

Abstract

3D Gaussian Splatting (3DGS) has demonstrated remarkable performance in novel view synthesis and 3D scene reconstruction, yet its quality often degrades in real-world environments due to transient distractors, such as moving objects and varying shadows. Existing methods commonly rely on semantic cues extracted from pre-trained vision models to identify and suppress these distractors, but such semantics are misaligned with the binary distinction between static and transient regions and remain fragile under the appearance perturbations introduced during 3DGS optimization. We propose 3DGS-HPC, a framework that circumvents these limitations 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.