Existing methods typically adopted a prior-based motion model ( e.g ., the local affine motion

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.

Specifically, ARTIC3D is built upon a skeleton-based surface representation and is further guided by 2D diffusion priors from Stable Diffusion. First, we enhance the input images with occlusions/truncation via 2D diffusion to obtain cleaner mask estimates and semantic features.

We present a method that reconstructs and animates a 3D head avatar from a single-view portrait image.

Recent advances in 3D-aware GAN models have enabled the generation of realistic and controllable human body images. However, existing methods focus on the control of major body joints, neglecting the manipulation of expressive attributes, such as facial expressions, jaw poses, hand poses, and so on.