2D Gaussian Splatting with Semantic Alignment for Image Inpainting
Abstract
A novel image inpainting framework using 2D Gaussian Splatting achieves competitive performance by combining continuous field representation with pretrained DINO model features for global semantic consistency.
Gaussian Splatting (GS), a recent technique for converting discrete points into continuous spatial representations, has shown promising results in 3D scene modeling and 2D image super-resolution. In this paper, we explore its untapped potential for image inpainting, which demands both locally coherent pixel synthesis and globally consistent semantic restoration. We propose the first image inpainting framework based on 2D Gaussian Splatting, which encodes incomplete images into a continuous field of 2D Gaussian splat coefficients and reconstructs the final image via a differentiable rasterization process. The continuous rendering paradigm of GS inherently promotes pixel-level coherence in the inpainted results. To improve efficiency and scalability, we introduce a patch-wise rasterization strategy that reduces memory overhead and accelerates inference. For global semantic consistency, we incorporate features from a pretrained DINO model. We observe that DINO's global features are naturally robust to small missing regions and can be effectively adapted to guide semantic alignment in large-mask scenarios, ensuring that the inpainted content remains contextually consistent with the surrounding scene. Extensive experiments on standard benchmarks demonstrate that our method achieves competitive performance in both quantitative metrics and perceptual quality, establishing a new direction for applying Gaussian Splatting to 2D image processing.
Community
We adapt 2D Gaussian Splatting to image inpainting by encoding incomplete images as continuous 2D GS parameters and reconstructing them via rasterization. The method incorporates DINO features for global semantic consistency and introduces patch-wise rasterization for efficiency, achieving competitive performance while establishing a new direction for applying GS to 2D image processing tasks.
The github repository is https://github.com/hitlhy715/2DGS_inpaint
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- High-fidelity 3D Gaussian Inpainting: preserving multi-view consistency and photorealistic details (2025)
- RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions (2025)
- DET-GS: Depth- and Edge-Aware Regularization for High-Fidelity 3D Gaussian Splatting (2025)
- SplatFill: 3D Scene Inpainting via Depth-Guided Gaussian Splatting (2025)
- GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors (2025)
- MagicRoad: Semantic-Aware 3D Road Surface Reconstruction via Obstacle Inpainting (2025)
- ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper