Paper Alert🚨 🤔What if 🦴rigging and 🎬animation could be generated together? Introducing ACT(SIGGRAPH 2026) — a unified framework for rigging, skinning, and animating 3D 「with any given skeletion topologies」 Soon available at Details👇

(1/5) Most existing pipelines handle rigging, skinning, and animation as separate steps. ACT treats them as complementary views of one process: shape → skeleton → deformation → motion A vision-language model provides semantic topology priors, while a diffusion transformer models skeletal structure and temporal motion in a shared latent space.

(2/5) Can one model rig characters with arbitrary topologies? ACT performs zero-shot rigging across humanoids, quadrupeds, mechanical objects, and arthropods. Compared with existing methods, ACT generates cleaner, more connected, and more semantically accurate skeletons.

(3/5) Rigging is not finished when the first skeleton is generated. With ACT, users can edit the skeletal topology with semantic instructions: “Add hair bones.” “Add skirt bones.” ACT then predicts the new joint locations and corresponding skinning weights. The same framework can also adapt a given skeleton template to characters with different body shapes.

(4/5) Once the character has a rig, describe the motion. “A snake was wriggling along with its head raised.” “A Tyrannosaurus rex walks forward and opens its mouth.” ACT generates topology-aware motion for very different characters.

(5/5) ACT can generate: • skeleton • skinning • text-driven motion Rigging and motion are generated together as one unified process. 📄:

Whoa that’s so cool

damn

Unified rigging and animation with any skeleton topology is gamechanging

bro is headless 😭

soon when?

Unified rigging skinning and animation with any skeleton topology is huge