We study the problem of inferring scene affordances by presenting a method for realistically
inserting people into scenes. Given a scene image with a marked region and an image of a …

In recent years, many deep learning based image inpainting methods have been developed
by the research community. Some of those methods have shown impressive image …

Deep image inpainting has made impressive progress with recent advances in image
generation and processing algorithms. We claim that the performance of inpainting …

Recent advancements in deep generative models have facilitated the creation of photo-
realistic images across various tasks. However, these generated images often exhibit …

The deep learning-based image inpainting models discussed in this review are critical
image processing techniques for filling in missing or removed regions in static planar …

Image and video inpainting is a classic problem in computer vision and computer graphics,
aiming to fill in the plausible and realistic content in the missing areas of images and videos …

Abstract Denoising Diffusion Probabilistic Models (DDPMs) have recently achieved
remarkable results in conditional and unconditional image generation. The pre-trained …

Wires and powerlines are common visual distractions that often undermine the aesthetics of
photographs. The manual process of precisely segmenting and removing them is extremely …

Compositing an object into an image involves multiple non-trivial sub-tasks such as object
placement and scaling, color/lighting harmonization, viewpoint/geometry adjustment, and …

Text-to-image generative models have attracted rising attention for flexible image editing via
user-specified descriptions. However, text descriptions alone are not enough to elaborate …