Segmentation of objects in a video is challenging due to the nuances suc...
Face parsing is defined as the per-pixel labeling of images containing h...
Large pre-trained vision-language models (VLMs) reduce the time for
deve...
The vision community has explored numerous pose guided human editing met...
The task of human reposing involves generating a realistic image of a pe...
Image-based virtual try-on involves synthesizing perceptually convincing...
Few-shot segmentation (FSS) methods perform image segmentation for a
par...
Image-based virtual try-on for fashion has gained considerable attention...