As information exists in various modalities in real world, effective interaction and fusion
among multimodal information plays a key role for the creation and perception of multimodal …

Perceiving the similarity between images has been a long-standing and fundamental
problem underlying various visual generation tasks. Predominant approaches measure the …

Video prediction is a challenging computer vision task that has a wide range of applications.
In this work, we present a new family of Transformer-based models for video prediction …

Leveraging StyleGAN's expressivity and its disentangled latent codes, existing methods can
achieve realistic editing of different visual attributes such as age and gender of facial …

Background Lung MRI with ultrashort echo times (UTEs) enables high-resolution and
radiation-free morphologic imaging; however, its image quality is still lower than that of CT …

Abstract 3D scene stylization aims to generate impressive stylized images from arbitrary
novel views based on the stylistic reference. Existing image-driven 3D scene stylization …

Guided image processing techniques are widely used to extract meaningful information from
a guiding image and facilitate the enhancement of the guided one. This paper specifically …

In this paper, we propose a new Transformer block for video future frames prediction based
on an efficient local spatial-temporal separation attention mechanism. Based on this new …

Real-scene image super-resolution aims to restore real-world low-resolution images into
their high-quality versions. A typical RealSR framework usually includes the optimization of …

A contrastive distortion‐level learning‐based no‐reference image‐quality assessment (NR‐
IQA) framework is proposed in this study to further effectively model various distortion types …