CoGeo-GS: Concept-Driven and Geometry-Aware Multi-Object Removal in 3D Scenes

Yuanxiang Ni; Xianliang Huang; Chenhang Ma; Chen Xiao; Yuewen Ma; Ruxin Wang; Hao Zhang

cs.CVAug 27, 2026

CoGeo-GS: Concept-Driven and Geometry-Aware Multi-Object Removal in 3D Scenes

Authors: Yuanxiang Ni, Xianliang Huang, Chenhang Ma, Chen Xiao, Yuewen Ma, Ruxin Wang, Hao Zhang

Organizations: Southern University of Science and Technology, Shenzhen, China · PICO, ByteDance, Beijing, China · Zhejiang University, Hangzhou, China · Fudan University, Shanghai, China · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China

Abstract

Multi-object removal in 3D scenes is challenging due to severe occlusions, semantic entanglement, and the difficulty of maintaining geometric and multi-view consistency. Existing 3D Gaussian Splatting (3DGS) methods perform well for single-object editing but scale poorly to multi-object scenarios, often requiring repetitive optimization and yielding unstable geometry in removed regions. We propose CoGeo-GS, a concept-driven framework for controllable multi-object removal in 3D scenes. CoGeo-GS assigns concept-aware semantic tags to Gaussians, enabling flexible object selection and reducing interference between foreground objects and background structures within a single optimization stage. To recover plausible geometry, we introduce a geometry-aware completion pipeline that combines monocular depth priors with diffusion-based refinement and boundary-aligned blending. A geometry-regularized refinement strategy further stabilizes reconstruction and preserves multi-view consistency. Experiments demonstrate that CoGeo-GS outperforms existing methods in visual quality and reconstruction fidelity.

Figures & tables

Fig. 1: Overview of the CoGeo-GS framework. (a) We first distill text-driven segmentation masks into 3D Gaussians to assign object-level identities. (b) Then, geometric voids are completed by conditioning a latent diffusion model on scale-aligned monocular depth priors (depth anchors) and VAE-encoded RGB latents. (c) The completed geometry is fused with the background via overlap-aware pruning. (d) A two-stage refinement strategy first optimizes appearance, then geometric constraint was subsequently employed to eliminate inconsistencies in fusion seams while preserving structural integrity.

Method	Task 1: Multi-Object Removal				Task 2: Single-Object Removal
Method	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	FID $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	FID $\downarrow$
GaussianEditor [ 2 ]	22.4	0.742	0.284	31.6	24.1	0.781	0.247	28.4
InFusion [ 10 ]	24.8	0.803	0.213	24.9	26.5	0.831	0.186	21.7
Gaussian Grouping [ 22 ]	25.6	0.821	0.198	22.8	27.3	0.847	0.172	19.6
SPIn-NeRF [ 13 ]	24.9	0.812	0.221	23.7	26.8	0.842	0.189	20.9
CoGeo-GS (Ours)	28.9	0.882	0.086	11.4	30.7	0.903	0.072	9.8

TABLE I: Quantitative comparison on multi-object and single-object removal tasks. Higher PSNR and SSIM indicate better rendering fidelity, while lower LPIPS and FID indicate better perceptual quality.

Fig. 2: Qualitative comparison on multi-object removal. We compare CoGeo-GS with GaussianEditor, InFusion and Gaussian Grouping in a consistent view.

Fig. 3: Qualitative comparison on single-object removal. We compare CoGeo-GS with SPIn-NeRF and InFusion in a consistent view.

Method	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	FID $\downarrow$
w/o concept-aware masking	26.85	0.851	0.112	16.90
w/o depth guidance	25.97	0.832	0.128	18.40
Full model (Ours)	28.90	0.882	0.086	11.40

TABLE II: Ablation study on the multi-object removal benchmark.

Fig. 4: Ablation study. Without concept-aware masking, residual artifacts persist in the edited regions. In the absence of depth guidance, the predicted depth map leads to blurred shadows and degraded structure in occluded areas.

Explore similar work

Semantic-Guided Progressive Object Removal with Gaussian Splatting
Jul 5, 2026Xianliang Huang, Chen Xiao, Yuanxiang Ni +53D Scene Editing Image Inpainting
PICO, ByteDance Inc. · Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences · Fudan University
3DTexMOR: 3D Gaussian Multi-Object Removal via Texture-Space Inpainting
Oct 8, 2026Kunxin Guang, Yonghao Zhao, Jian Yang +13D Scene Completion 3D Gaussian Splatting
Nanjing University · Nankai University
CoIn: Comprehensive 2D-3D Inpainting with Gaussian Splatting Guidance
Jun 25, 2026Hana Kim, Minje Kim, Tae-Kyun Kim3D Gaussian Splatting 3D Scene Editing
LG Electronics, Seoul, South Korea · KAIST, Daejeon, South Korea

Jul 5, 2026J/K move · Enter open · S save

Semantic-Guided Progressive Object Removal with Gaussian Splatting

Xianliang Huang, Chen Xiao, Yuanxiang Ni, Guanming Liu+4

PICO, ByteDance Inc. · Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences · Fudan University

3D Scene Editing Image Inpainting

Open paper AskPDF arXiv

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.

Abstract

Explore similar work

Semantic-Guided Progressive Object Removal with Gaussian Splatting

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

CoIn: Comprehensive 2D-3D Inpainting with Gaussian Splatting Guidance