Perspective-aware 3D Gaussian Inpainting with Multi-view Consistency

• URL: http://arxiv.org/abs/2510.10993v1
• Date: Mon, 13 Oct 2025 04:10:39 GMT
• Title: Perspective-aware 3D Gaussian Inpainting with Multi-view Consistency
• Authors: Yuxin Cheng, Binxiao Huang, Taiqiang Wu, Wenyong Zhou, Chenchen Ding, Zhengwu Liu, Graziano Chesi, Ngai Wong,
• Abstract summary: We present PAInpainter, a novel approach designed to advance 3D Gaussian inpainting by leveraging perspective-aware content propagation and consistency verification across multi-view inpainted images.<n>Our approach achieves superior 3D inpainting quality, with PSNR scores of 26.03 dB and 29.51 dB on the SPIn-NeRF and NeRFiller datasets, respectively.
• Score: 22.654962078504017
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D Gaussian inpainting, a critical technique for numerous applications in virtual reality and multimedia, has made significant progress with pretrained diffusion models. However, ensuring multi-view consistency, an essential requirement for high-quality inpainting, remains a key challenge. In this work, we present PAInpainter, a novel approach designed to advance 3D Gaussian inpainting by leveraging perspective-aware content propagation and consistency verification across multi-view inpainted images. Our method iteratively refines inpainting and optimizes the 3D Gaussian representation with multiple views adaptively sampled from a perspective graph. By propagating inpainted images as prior information and verifying consistency across neighboring views, PAInpainter substantially enhances global consistency and texture fidelity in restored 3D scenes. Extensive experiments demonstrate the superiority of PAInpainter over existing methods. Our approach achieves superior 3D inpainting quality, with PSNR scores of 26.03 dB and 29.51 dB on the SPIn-NeRF and NeRFiller datasets, respectively, highlighting its effectiveness and generalization capability.

Related papers

• Wonder3D++: Cross-domain Diffusion for High-fidelity 3D Generation from a Single Image [68.55613894952177]
  We introduce textbfWonder3D++, a novel method for efficiently generating high-fidelity textured meshes from single-view images.<n>We propose a cross-domain diffusion model that generates multi-view normal maps and the corresponding color images.<n> Lastly, we introduce a cascaded 3D mesh extraction algorithm that drives high-quality surfaces from the multi-view 2D representations in only about $3$ minute in a coarse-to-fine manner.
  arXiv  Detail & Related papers  (2025-11-03T17:24:18Z)
• High-fidelity 3D Gaussian Inpainting: preserving multi-view consistency and photorealistic details [8.279171283542066]
  Inpainting 3D scenes remains a challenging task due to the inherent irregularity of 3D structures.<n>We propose a novel 3D Gaussian inpainting framework that reconstructs complete 3D scenes by leveraging sparse inpainted views.<n>Our approach outperforms existing state-of-the-art methods in both visual quality and view consistency.
  arXiv  Detail & Related papers  (2025-07-24T01:48:50Z)
• 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)
• EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [61.1662426227688]
  Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization.<n>We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
  arXiv  Detail & Related papers  (2025-03-26T02:47:27Z)
• 3D Gaussian Inpainting with Depth-Guided Cross-View Consistency [30.951440204237166]
  We propose a framework of 3D Gaussian Inpainting with Depth-Guided Cross-View Consistency (3DGIC) for cross-view consistent 3D inpainting.<n>Our 3DGIC exploits background pixels visible across different views for updating the inpainting mask, allowing us to refine the 3DGS for inpainting purposes.
  arXiv  Detail & Related papers  (2025-02-17T13:46:47Z)
• InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior [36.23604779569843]
  3D Gaussians have recently emerged as an efficient representation for novel view synthesis. This work studies its editability with a particular focus on the inpainting task. Compared to 2D inpainting, the crux of inpainting 3D Gaussians is to figure out the rendering-relevant properties of the introduced points.
  arXiv  Detail & Related papers  (2024-04-17T17:59:53Z)
• HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models [59.01600111737628]
  HD-Painter is a training free approach that accurately follows prompts and coherently scales to high resolution image inpainting. To this end, we design the Prompt-Aware Introverted Attention (PAIntA) layer enhancing self-attention scores. Our experiments demonstrate that HD-Painter surpasses existing state-of-the-art approaches quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2023-12-21T18:09:30Z)
• Wonder3D: Single Image to 3D using Cross-Domain Diffusion [105.16622018766236]
  Wonder3D is a novel method for efficiently generating high-fidelity textured meshes from single-view images. To holistically improve the quality, consistency, and efficiency of image-to-3D tasks, we propose a cross-domain diffusion model.
  arXiv  Detail & Related papers  (2023-10-23T15:02:23Z)
• IT3D: Improved Text-to-3D Generation with Explicit View Synthesis [71.68595192524843]
  This study presents a novel strategy that leverages explicitly synthesized multi-view images to address these issues. Our approach involves the utilization of image-to-image pipelines, empowered by LDMs, to generate posed high-quality images. For the incorporated discriminator, the synthesized multi-view images are considered real data, while the renderings of the optimized 3D models function as fake data.
  arXiv  Detail & Related papers  (2023-08-22T14:39:17Z)

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.