Diffusion models are now the undisputed state-of-the-art for image generation and image restoration. However, they require large amounts of computational power for training and inference. In this paper, we propose lightweight diffusion models for image inpainting that can be trained on a single image, or a few images. We show that our approach competes with large state-of-the-art models in specific cases. We also show that training a model on a single image is particularly relevant for image acquisition modality that differ from the RGB images of standard learning databases. We show results in three different contexts: texture images, line drawing images, and materials BRDF, for which we achieve state-of-the-art results in terms of realism, with a computational load that is greatly reduced compared to concurrent methods.

翻译：扩散模型现已成为图像生成与图像修复领域无可争议的最先进技术。然而，其在训练与推断阶段均需消耗大量计算资源。本文提出一种轻量级扩散模型，可用于单幅图像或少量图像的修复训练。实验表明，在特定场景下，本方法可与当前大型先进模型相媲美。同时，我们论证了单图像训练模式对于非标准学习数据库RGB图像采集模态的独特适应性。我们在纹理图像、线稿图像及材料双向反射分布函数三类场景中进行了验证，在显著降低计算负荷的同时，所获结果的真实度达到了当前最优水平。