Benchmarking Single-Step Inpainting Methods for Multi-Object 3D Gaussian Splatting Scenes

• URL: http://arxiv.org/abs/2605.30987v1
• Date: Fri, 29 May 2026 08:24:16 GMT
• Title: Benchmarking Single-Step Inpainting Methods for Multi-Object 3D Gaussian Splatting Scenes
• Abstract summary: Reconstruction-based inpainters outperform generative diffusion models in 3D consistency.<n>Using a state-of-the-art generative 2D inpainter, we create a straightforward baseline to underline the importance of object removal before inpainting in the 3D setting.
• Score: 43.95837214164744
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The tasks of object removal and inpainting 3D Gaussian Splatting (3DGS) scenes face challenges such as 3D consistency across camera views. In comparing 2D inpainters and their suitability for the 3D domain, we find that reconstruction-based inpainters outperform generative diffusion models in 3D consistency. Integrating these 2D inpainters into different single-step methods for creating and finetuning 3DGS scenes, our results indicate that initializing the scene from scratch produces higher quality results than finetuning the existing scene. Using a state-of-the-art generative 2D inpainter, we create a straightforward baseline to underline the importance of object removal before inpainting in the 3D setting. Since 360° datasets rarely include real-world ground truths, and challenging occlusion scenarios are equally sparse, we introduce a novel multi-object scene with recorded ground truth data and many views with object occlusions.

Related papers

• CoIn: Comprehensive 2D-3D Inpainting with Gaussian Splatting Guidance [33.42204651464501]
  CoIn is a framework that bridges 2D inpainting models and 3DGS through a multi-stage consistency pipeline.<n>We introduce Reference Adaptive GS with Feature Attention to reconstruct a coarse 3D scene by adaptively weighing towards a reference view (2D -> 3D)<n>Finally, a Texture-Enhancing Discriminator refines the 3D scene to achieve high photometric realism (2D -> 3D)
  arXiv  Detail & Related papers  (2026-06-25T22:24:27Z)
• ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models [76.80262068405243]
  3D inpainting often relies on multi-view 2D image inpainting, where inherent inconsistencies result in blurred textures, spatial discontinuities, and distracting visual artifacts.<n>We propose Filler-3D, a novel method designed for the completion and editing of high-quality and consistent 3D objects.<n>We analyze the representation gap between 3D and videos, and propose an adaptation of a video inpainting model for 3D scene inpainting.
  arXiv  Detail & Related papers  (2025-08-25T17:59:40Z)
• Constructing a 3D Scene from a Single Image [31.11317559252235]
  SceneFuse-3D is a training-free framework designed to synthesize coherent 3D scenes from a single top-down view.<n>We decompose the input image into overlapping regions and generate each using a pretrained 3D object generator.<n>This modular design allows us to overcome resolution bottlenecks and preserve spatial structure without requiring 3D supervision or fine-tuning.
  arXiv  Detail & Related papers  (2025-05-21T17:10:47Z)
• Visibility-Uncertainty-guided 3D Gaussian Inpainting via Scene Conceptional Learning [63.94919846010485]
  3D Gaussian inpainting (3DGI) is challenging in effectively leveraging complementary visual and semantic cues from multiple input views.<n>We propose a method that measures the visibility uncertainties of 3D points across different input views and uses them to guide 3DGI.<n>We build a novel 3DGI framework, VISTA, by integrating VISibility-uncerTainty-guided 3DGI with scene conceptuAl learning.
  arXiv  Detail & Related papers  (2025-04-23T06:21:11Z)
• Zero-Shot Multi-Object Scene Completion [59.325611678171974]
  We present a 3D scene completion method that recovers the complete geometry of multiple unseen objects in complex scenes from a single RGB-D image. Our method outperforms the current state-of-the-art on both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2024-03-21T17:59:59Z)
• NeRFiller: Completing Scenes via Generative 3D Inpainting [113.18181179986172]
  We propose NeRFiller, an approach that completes missing portions of a 3D capture via generative 3D inpainting. In contrast to related works, we focus on completing scenes rather than deleting foreground objects.
  arXiv  Detail & Related papers  (2023-12-07T18:59:41Z)
• CC3D: Layout-Conditioned Generation of Compositional 3D Scenes [49.281006972028194]
  We introduce CC3D, a conditional generative model that synthesizes complex 3D scenes conditioned on 2D semantic scene layouts. Our evaluations on synthetic 3D-FRONT and real-world KITTI-360 datasets demonstrate that our model generates scenes of improved visual and geometric quality.
  arXiv  Detail & Related papers  (2023-03-21T17:59:02Z)
• SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fields [26.296017756560467]
  In 3D, solutions must be consistent across multiple views and geometrically valid. We propose a novel 3D inpainting method that addresses these challenges. We first demonstrate the superiority of our approach on multiview segmentation, comparing to NeRFbased methods and 2D segmentation approaches.
  arXiv  Detail & Related papers  (2022-11-22T13:14:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.