With the proposed novel sampling strategy, our model achieves instance-aware colorization in diverse and complex scenarios.

We present a novel alignment-before-generation approach to tackle the challenging task of generating general 3D shapes based on 2D images or texts.

The latter usually defines the protein's key function, but cannot

Our framework empowers InsActor to capture complex relationships between high-level human instructions and character motions by employing diffusion policies for flexibly conditioned motion planning.

They map random samples (seeds) from a high-dimensional space, conditioned on a user-provided text prompt, to a corresponding image.

These authors contributed equally to this work.