3DTexMOR: 3D Gaussian Multi-Object Removal via Texture-Space Inpainting

2026-10-08

AI Summary

This study addresses the challenge of multi-object removal, where limited viewpoints frequently induce 2D inpainting artifacts and cross-view inconsistencies. To overcome these limitations, this work proposes a unified texture-space inpainting paradigm based on 3D Gaussian Splatting. Specifically, it aggregates multi-view observations to complete missing regions and introduces view-independent intrinsic attribute decoupling to eliminate specular highlight interference. Furthermore, geometric regularization constraints are incorporated to supervise scene completion, ensuring both geometric and appearance consistency. Experimental results demonstrate that the proposed method achieves visually plausible scene completion, improving PSNR by 5.8 dB and reducing LPIPS by over 22%, thereby establishing state-of-the-art performance on multi-object removal tasks.

Abstract

3D object removal aims to remove target objects from reconstructed scenes and complete the geometry and appearance of occluded regions. Existing NeRF- and 3DGS-based methods typically inpaint 2D images to guide 3D completion. However, complex multi-object layouts limit the surrounding context visible in each view, making 2D inpainting prone to artifacts. Inconsistent completions across views also introduce conflicting supervision and blurry reconstructions. We propose 3D Gaussian Multi-Object Removal via Texture-Space Inpainting (3DTexMOR). Our key idea is to perform inpainting in a unified texture space shared by all views. By combining complementary observations, this space provides richer context for recovering missing regions and promotes cross-view appearance consistency. We aggregate multi-view observations into texture maps, inpaint the missing regions, and reproject the completed maps into camera views to supervise Gaussian scene completion. To avoid the influence of view-dependent highlights and reflections, we decompose appearance and aggregate view-independent intrinsic attributes instead of RGB colors. We further introduce geometrically regularized Gaussian completion to constrain the geometry of the completed regions. Extensive experiments demonstrate visually plausible completions and state-of-the-art multi-object removal performance, improving PSNR by 5.8 dB and reducing LPIPS by at least 22% compared with existing methods.

Problem

• 3D object removal
• multi-object removal
• texture-space inpainting
• 3D Gaussian Splatting
• view consistency

Innovation

• Texture-Space Inpainting
• Multi-Object Removal
• 3D Gaussian Splatting
• Appearance Decomposition
• Geometric Regularization