Deep image inpainting can inpaint a corrupted image using a feed-forward inference, but
still fails to handle large missing area or complex semantics. Recently, GAN inversion based …

Conventional deep image inpainting methods are based on auto-encoder architecture, in
which the spatial details of images will be lost in the down-sampling process, leading to the …

The recent success of text-to-image generation diffusion models has also revolutionized
semantic image editing, enabling the manipulation of images based on query/target texts …

Vision transformers (ViT) usually extract features via forwarding all the tokens in the self-
attention layers from top to toe. In this paper, we introduce dynamic token-pass vision …

Controllable image synthesis is a method by which users can manipulate a particular
attribute in an image in a semantically meaningful way without affecting other attributes. This …

Most existing inpainting methods repair a corrupted image to a single output, which gives
people no choice to select the most satisfactory result. However, image inpainting is …

Object removal refers to the process of erasing designated objects from an image while
preserving the overall appearance. The performance of an object remover is quantitatively …

Image synthesis based on natural language description has become a research hotspot in
edge computing in artificial intelligence. With the help of generative adversarial edge …

Recently, foundation models trained on massive datasets to adapt to a wide range of tasks
have attracted considerable attention and are actively being explored within the computer …

In order to eliminate the influence of moving targets in visual positioning, a dynamic object
filtering approach based on object detection and inter‐frame geometric constraints is …