The creation of an image from another and from different types of data including text, scene
graph, and object layout, is one of the very challenging tasks in computer vision. In addition …

In the text-to-image generation field, recent remarkable progress in Stable Diffusion makes it
possible to generate rich kinds of novel photorealistic images. However, current models still …

Dynamic scene graph generation aims at generating a scene graph of the given video.
Compared to the task of scene graph generation from images, it is more challenging …

Diffusion models (DMs) have shown great potential for high-quality image synthesis.
However, when it comes to producing images with complex scenes, how to properly …

Text-to-image synthesis (T2I) aims to generate photo-realistic images which are
semantically consistent with the text descriptions. Existing methods are usually built upon …

With the surge in autonomous driving technologies, the reliance on comprehensive and high-
definition bird's-eye-view (BEV) representations has become paramount. This burgeoning …

We propose a new framework for conditional image synthesis from semantic layouts of any
precision levels, ranging from pure text to a 2D semantic canvas with precise shapes. More …

Layout-to-image generation refers to the task of synthesizing photo-realistic images based
on semantic layouts. In this paper, we propose LayoutDiffuse that adapts a foundational …

We present a method that achieves state-of-the-art results on challenging (few-shot) layout-
to-image generation tasks by accurately modeling textures, structures and relationships …

Generating images from graph-structured inputs, such as scene graphs, is uniquely
challenging due to the difficulty of aligning nodes and connections in graphs with objects …