Inpaint360GS: Efficient Object-Aware 3D Inpainting via Gaussian Splatting for 360{\deg} Scenes

TL;DR

Inpaint360GS introduces a novel 3D Gaussian Splatting-based framework for efficient, high-quality object-aware inpainting in 360-degree scenes, addressing challenges of object identification, occlusion, and view consistency.

Contribution

The paper presents Inpaint360GS, a new 3D inpainting method that enables multi-object removal and scene completion in 360 scenes by integrating 2D segmentation with 3D Gaussian Splatting.

Findings

Outperforms existing inpainting methods on 360 scenes

Achieves high-fidelity, view-consistent scene completion

Introduces a new dataset for 360-degree inpainting

Abstract

Despite recent advances in single-object front-facing inpainting using NeRF and 3D Gaussian Splatting (3DGS), inpainting in complex 360{\deg} scenes remains largely underexplored. This is primarily due to three key challenges: (i) identifying target objects in the 3D field of 360{\deg} environments, (ii) dealing with severe occlusions in multi-object scenes, which makes it hard to define regions to inpaint, and (iii) maintaining consistent and high-quality appearance across views effectively. To tackle these challenges, we propose Inpaint360GS, a flexible 360{\deg} editing framework based on 3DGS that supports multi-object removal and high-fidelity inpainting in 3D space. By distilling 2D segmentation into 3D and leveraging virtual camera views for contextual guidance, our method enables accurate object-level editing and consistent scene completion. We further introduce a new dataset tailored for 360{\deg} inpainting, addressing the lack of ground truth object-free scenes. Experiments demonstrate that Inpaint360GS outperforms existing baselines and achieves state-of-the-art performance. Project page: https://dfki-av.github.io/inpaint360gs/