GuidPaint: Class-Guided Image Inpainting with Diffusion Models
Qimin Wang, Xinda Liu, Guohua Geng

TL;DR
GuidPaint introduces a class-guided, training-free image inpainting method using diffusion models, offering precise control over masked regions and improved semantic and visual quality without additional training.
Contribution
It presents a novel class-guided framework that enhances diffusion-based inpainting with fine-grained control, eliminating the need for retraining or architectural modifications.
Findings
Outperforms existing context-aware methods in qualitative assessments.
Achieves higher quantitative scores in inpainting tasks.
Enables user-controlled intermediate results with stochastic and deterministic sampling.
Abstract
In recent years, diffusion models have been widely adopted for image inpainting tasks due to their powerful generative capabilities, achieving impressive results. Existing multimodal inpainting methods based on diffusion models often require architectural modifications and retraining, resulting in high computational cost. In contrast, context-aware diffusion inpainting methods leverage the model's inherent priors to adjust intermediate denoising steps, enabling high-quality inpainting without additional training and significantly reducing computation. However, these methods lack fine-grained control over the masked regions, often leading to semantically inconsistent or visually implausible content. To address this issue, we propose GuidPaint, a training-free, class-guided image inpainting framework. By incorporating classifier guidance into the denoising process, GuidPaint enables…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
