Online Exemplar Fine-Tuning for Image-to-Image Translation
This work addresses the limited applicability and generalization of existing exemplar-based image-to-image translation techniques for researchers and practitioners by eliminating the need for domain-specific and task-specific training.
This paper introduces Online Exemplar Fine-Tuning (OEFT), a novel framework for exemplar-based image-to-image translation that fine-tunes off-the-shelf networks directly on input image pairs without an offline training phase. OEFT demonstrates superior generalization to unseen image pairs and outperforms existing state-of-the-art methods that require intensive training.
Existing techniques to solve exemplar-based image-to-image translation within deep convolutional neural networks (CNNs) generally require a training phase to optimize the network parameters on domain-specific and task-specific benchmarks, thus having limited applicability and generalization ability. In this paper, we propose a novel framework, for the first time, to solve exemplar-based translation through an online optimization given an input image pair, called online exemplar fine-tuning (OEFT), in which we fine-tune the off-the-shelf and general-purpose networks to the input image pair themselves. We design two sub-networks, namely correspondence fine-tuning and multiple GAN inversion, and optimize these network parameters and latent codes, starting from the pre-trained ones, with well-defined loss functions. Our framework does not require the off-line training phase, which has been the main challenge of existing methods, but the pre-trained networks to enable optimization in online. Experimental results prove that our framework is effective in having a generalization power to unseen image pairs and clearly even outperforms the state-of-the-arts needing the intensive training phase.