CoIn: Comprehensive 2D-3D Inpainting with Gaussian Splatting Guidance
Quick Answer
CoIn introduces a multi-stage framework for 2D-3D inpainting, utilizing Gaussian Splatting for enhanced scene reconstruction.
Quick Take
CoIn introduces a multi-stage framework for 2D-3D inpainting, utilizing Gaussian Splatting for enhanced scene reconstruction. It achieves state-of-the-art performance in both object removal and insertion tasks, leveraging a diffusion model and adaptive feature attention for consistency across views.
Key Points
- CoIn bridges 2D inpainting and 3D Gaussian Splatting through a novel pipeline.
- Initial inpainting uses a diffusion model, allowing arbitrary-shaped masks.
- Reference Adaptive GS with Feature Attention reconstructs coarse 3D scenes.
- Achieves high photometric realism with a Texture-Enhancing Discriminator.
- Effectively handles both object removal and insertion tasks.
Paper Resources
📖 Reader Mode
~2 min readAbstract:3D scene inpainting is essential for reconstructing areas corrupted by occlusions or limited viewpoints. While recent methods leverage Gaussian Splatting (GS) for efficient 3D editing, they often depend on precise multi-view segmentation masks and are inherently constrained to object removal tasks. We propose CoIn, a novel framework that bridges 2D inpainting models and 3DGS through a multi-stage consistency pipeline. Our approach first generates initial inpainted images using a diffusion model, enabling the use of arbitrary-shaped masks and diverse tasks like object insertion. We then introduce Reference Adaptive GS with Feature Attention to reconstruct a coarse 3D scene by adaptively weighing towards a reference view (2D -> 3D). This 3D representation provides geometric guidance to the diffusion process via GS-based Reference Feature Warping, ensuring multi-view consistency (3D -> 2D). Finally, a Texture-Enhancing Discriminator refines the 3D scene to achieve high photometric realism (2D -> 3D). Experiments show that CoIn, effectively leveraging bidirectional information flow, achieves state-of-the-art performance and effectively handles both object removal and object insertion with flexible mask input.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.27584 [cs.CV] |
| (or arXiv:2606.27584v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2606.27584 arXiv-issued DOI via DataCite |
Submission history
From: Hana Kim [view email]
[v1]
Thu, 25 Jun 2026 22:24:27 UTC (45,292 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
A phase-aware LLM agent optimizes human-object interaction retrieval, outperforming Optuna TPE by 33.3% and VDTuner by 34.2% on the HICO-DET benchmark. This method enhances throughput by 15.3x over UniIR and demonstrates strong transferability across vector database management systems.