Synthesizing visual content that meets users' needs often requires flexible and precise
controllability of the pose, shape, expression, and layout of the generated objects. Existing …

Generative adversarial networks (GANs) have drawn enormous attention due to their simple
yet effective training mechanism and superior image generation quality. With the ability to …

Videos show continuous events, yet most--if not all--video synthesis frameworks treat them
discretely in time. In this work, we think of videos of what they should be--time-continuous …

A recent trend in generative modeling is building 3D-aware generators from 2D image
collections. To induce the 3D bias, such models typically rely on volumetric rendering, which …

Text-to-image generative models often reflect the biases of the training data, leading to
unequal representations of underrepresented groups. This study investigates inclusive text …

The diffusion model has long been plagued by scalability and quadratic complexity issues,
especially within transformer-based structures. In this study, we aim to leverage the long …

We present DiffCollage, a compositional diffusion model that can generate large content by
leveraging diffusion models trained on generating pieces of the large content. Our approach …

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 …

Toward infinite-scale 3D city synthesis, we propose a novel framework, InfiniCity, which
constructs and renders an unconstrainedly large and 3D-grounded environment from …

Diffusion models have demonstrated remarkable performance in image and video synthesis.
However scaling them to high-resolution inputs is challenging and requires restructuring the …