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

2026-03-08

AI Summary

Transient disturbances such as moving objects and dynamic shadows in real-world scenes significantly degrade the reconstruction quality of 3D Gaussian splatting. To address this issue, this work proposes a local image patch classification mechanism that operates without requiring pretrained semantic models. By integrating photometric consistency with perceptual features, the method constructs an adaptive hybrid discriminative criterion to robustly distinguish between static and transient regions. This approach effectively mitigates semantic misalignment caused by appearance perturbations and substantially enhances interference rejection across multiple real-world scenes, yielding higher-quality novel view synthesis results.

Technology Category

• Computer Vision: 3D Computer Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• 3D Gaussian Splatting
• transient distractors
• novel view synthesis
• 3D scene reconstruction
• moving objects

Innovation

• 3D Gaussian Splatting
• distractor removal
• patch-wise classification
• hybrid metric
• novel view synthesis