Related papers: What Decreases Editing Capability? Domain-Specific…
The extraction and proper utilization of convolution neural network (CNN) features have a significant impact on the performance of image super-resolution (SR). Although CNN features contain both the spatial and channel information, current…
Existing GAN inversion methods are stuck in a paradox that the inverted codes can either achieve high-fidelity reconstruction, or retain the editing capability. Having only one of them clearly cannot realize real image editing. In this…
Recent advancements in real image editing have been attributed to the exploration of Generative Adversarial Networks (GANs) latent space. However, the main challenge of this procedure is GAN inversion, which aims to map the image to the…
Synthesizing high-quality, realistic images from text-descriptions is a challenging task, and current methods synthesize images from text in a multi-stage manner, typically by first generating a rough initial image and then refining image…
Reference-guided image generation has progressed rapidly, yet current diffusion models still struggle to preserve fine-grained visual details when refining a generated image using a reference. This limitation arises because VAE-based latent…
Recent years have seen more and more demand for a unified framework to address multiple realistic image retrieval tasks concerning both category and attributes. Considering the scale of modern datasets, hashing is favorable for its low…
Historical Document Image Binarization is a well-known segmentation problem in image processing. Despite ubiquity, traditional thresholding algorithms achieved limited success on severely degraded document images. With the advent of deep…
Specular highlight removal plays a pivotal role in multimedia applications, as it enhances the quality and interpretability of images and videos, ultimately improving the performance of downstream tasks such as content-based retrieval,…
Without sufficient data, the quantity of information available for supervised training is constrained, as obtaining sufficient synthetic aperture radar (SAR) training data in practice is frequently challenging. Therefore, current SAR…
In StyleGAN, convolution kernels are shaped by both static parameters shared across images and dynamic modulation factors $w^+\in\mathcal{W}^+$ specific to each image. Therefore, $\mathcal{W}^+$ space is often used for image inversion and…
Unified multimodal models (UMMs) integrate visual understanding and generation within a single framework. For text-to-image (T2I) tasks, this unified capability allows UMMs to refine outputs after their initial generation, potentially…
Intrinsic image decomposition is the process of separating the reflectance and shading layers of an image, which is a challenging and underdetermined problem. In this paper, we propose to systematically address this problem using a deep…
Removing degradation from document images not only improves their visual quality and readability, but also enhances the performance of numerous automated document analysis and recognition tasks. However, existing regression-based methods…
Facial attribute editing aims to modify target attributes while preserving attribute-irrelevant content and overall image fidelity. Existing GAN-based methods provide favorable controllability, but often suffer from weak alignment between…
High Dynamic Range (HDR) imaging aims to reproduce the wide range of brightness levels present in natural scenes, which the human visual system can perceive but conventional digital cameras often fail to capture due to their limited dynamic…
Low-light image enhancement aims to improve an image's visibility while keeping its visual naturalness. Different from existing methods tending to accomplish the relighting task directly by ignoring the fidelity and naturalness recovery, we…
In recent years, conditional image synthesis has attracted growing attention due to its controllability in the image generation process. Although recent works have achieved realistic results, most of them have difficulty handling…
Many real-world applications, such as interactive photo retouching, artistic content creation, and product design, require flexible and iterative image editing. However, existing image editing methods primarily focus on achieving the…
Fine-tuning pre-trained neural network models has become a widely adopted approach across various domains. However, it can lead to the distortion of pre-trained feature extractors that already possess strong generalization capabilities.…
Digital imaging aims to replicate realistic scenes, but Low Dynamic Range (LDR) cameras cannot represent the wide dynamic range of real scenes, resulting in under-/overexposed images. This paper presents a deep learning-based approach for…