Semantic-Guided Progressive Object Removal with Gaussian Splatting
For AR/VR, robotics, and digital content creation, this work addresses the challenge of removing objects from 3D scenes with better handling of complex geometry and textures, though it is an incremental improvement over existing Gaussian-based methods.
The paper tackles 3D object removal from reconstructed scenes, proposing a method that uses semantic guidance and progressive refinement to improve perceptual quality and cross-view consistency. Experiments show it outperforms existing Gaussian-based methods.
Removing unwanted objects from reconstructed 3D scenes is an important task in computer vision, supporting applications in AR/VR, robotics, and digital content creation. Existing methods typically complete the entire masked region in a single step and without effectively utilizing semantic information from other views, leading to difficulties in handling complex geometric details and textures. In this work, we propose a novel framework that integrates Semantic-guided Block Matching (SBM) and Region-Wise Progressive Refinement (RPR) for high-quality 3D object removal. First, we leverage DINOv2 to encode semantic guidance from multi-view observations, and the best match tokens are decoded to complete missing regions in the target view while maintaining cross-view consistency. Second, we introduce a RPR strategy that segments the target mask into multiple subregions and selectively refines those with poor visual quality. Our method is built upon Gaussian Splatting, ensuring high-fidelity scene reconstruction with efficient computation. Experimental results demonstrate that our approach outperforms existing Gaussian-based methods in terms of perceptual quality and coherence in 3D object removal.