Recent advances in machine learning have led to increased interest in solving visual
computing problems using methods that employ coordinate‐based neural networks. These …

Image-to-image translation (I2I) aims to transfer images from a source domain to a target
domain while preserving the content representations. I2I has drawn increasing attention and …

Supervised image-to-image translation has been proven to generate realistic images with
sharp details and to have good quantitative performance. Such methods are trained on a …

Abstract Conditional Generative Adversarial Networks (cGANs) have enabled controllable
image synthesis for many computer vision and graphics applications. However, recent …

During image editing, existing deep generative models tend to re-synthesize the entire
output from scratch, including the unedited regions. This leads to a significant waste of …

Generative models operate at fixed resolution, even though natural images come in a variety
of sizes. As high-resolution details are downsampled away and low-resolution images are …

Abstract Implicit Neural Spatial Representation (INSR) has emerged as an effective
representation of spatially-dependent vector fields. This work explores solving time …

To segment 4K or 6K ultra high-resolution images needs extra computation consideration in
image segmentation. Common strategies, such as down-sampling, patch cropping, and …

Image inpainting aims to fill the missing hole of the input. It is hard to solve this task
efficiently when facing high-resolution images due to two reasons:(1) Large reception field …

Hyperspectral image (HSI) super-resolution (SR) without additional auxiliary image remains
a constant challenge due to its high-dimensional spectral patterns, where learning an …