Diffusion models usher a new era of video editing, flexibly manipulating the video contents
with text prompts. Despite the widespread application demand in editing human-centered …

Portrait harmonization aims to composite a subject into a new background adjusting its
lighting and color to ensure harmony with the background scene. Existing harmonization …

Indonesian Journal of Computer Science Page 1 Indonesian Journal of Computer Science
ISSN 2549-7286 (online) Jln. Khatib Sulaiman Dalam No. 1, Padang, Indonesia Website …

Deep networks have shown impressive performance in the image restoration tasks, such as
image colorization. However, we find that previous approaches rely on the digital …

Deep learning methods have significantly advanced the performance of image matting.
However, dataset biases can mislead the matting models to biased behavior. In this paper …

Image compositing plays a vital role in photo editing. After inserting a foreground object into
another background image, the composite image may look unnatural and inharmonious …

We propose a method for lighting and shadow editing of outdoor disharmonious composite
images, including foreground harmonization and cast shadow generation. Most existing …

Image harmonization aims to seamlessly integrate foreground and background elements
from distinct photos into a visually realistic composite. However, achieving high-quality …

Object-centric architectures can learn to extract distinct object representations from visual
scenes, enabling downstream applications on the object level. Similarly to autoencoder …

Image composition involves extracting a foreground object from one image and pasting it
into another image through Image harmonization algorithms (IHAs), which aim to adjust the …