Image generation models have made remarkable progress, and image evaluation is crucial for explaining and driving the development of these models. Previous studies have extensively explored human and automatic evaluations of image generation. Herein, these studies are comprehensively surveyed, specifically for two main parts: evaluation protocols and evaluation methods. First, 10 image generation tasks are summarized with focus on their differences in evaluation aspects. Based on this, a novel protocol is proposed to cover human and automatic evaluation aspects required for various image generation tasks. Second, the review of automatic evaluation methods in the past five years is highlighted. To our knowledge, this paper presents the first comprehensive summary of human evaluation, encompassing evaluation methods, tools, details, and data analysis methods. Finally, the challenges and potential directions for image generation evaluation are discussed. We hope that this survey will help researchers develop a systematic understanding of image generation evaluation, stay updated with the latest advancements in the field, and encourage further research.

Denoising Diffusion models have exhibited remarkable capabilities in image generation. However, generating high-quality samples requires a large number of iterations. Knowledge distillation for diffusion models is an effective method to address this limitation with a shortened sampling process but causes degraded generative quality. Based on our analysis with bias-variance decomposition and experimental observations, we attribute the degradation to the spatial fitting error occurring in the training of both the teacher and student model in the distillation. Accordingly, we propose Spatial Fitting-Error Reduction Distillation model (SFERD). SFERD utilizes attention guidance from the teacher model and a designed semantic gradient predictor to reduce the student's fitting error. Empirically, our proposed model facilitates high-quality sample generation in a few function evaluations. We achieve an FID of 5.31 on CIFAR-10 and 9.39 on ImageNet 64x64 with only one step, outperforming existing diffusion methods. Our study provides a new perspective on diffusion distillation by highlighting the intrinsic denoising ability of models.

Deep generative models are effective in style transfer. Previous methods learn one or several specific artist-style from a collection of artworks. These methods not only homogenize the artist-style of different artworks of the same artist but also lack generalization for the unseen artists. To solve these challenges, we propose a double-style transferring module (DSTM). It extracts different artist-style and artwork-style from different artworks (even untrained) and preserves the intrinsic diversity between different artworks of the same artist. DSTM swaps the two styles in the adversarial training and encourages realistic image generation given arbitrary style combinations. However, learning style from single artwork can often cause over-adaption to it, resulting in the introduction of structural features of style image. We further propose an edge enhancing module (EEM) which derives edge information from multi-scale and multi-level features to enhance structural consistency. We broadly evaluate our method across six large-scale benchmark datasets. Empirical results show that our method achieves arbitrary artist-style and artwork-style extraction from a single artwork, and effectively avoids introducing the style image’s structural features. Our method improves the state-of-the-art deception rate from 58.9% to 67.2% and the average FID from 48.74 to 42.83.