Retargeting News
The latest Retargeting coverage curated for game developers.
arXiv cs.GR details PDB, a facial animation retargeting method that blends deformed control points to move expressions across mismatched meshes. It computes target weights once, reuses them per character, and …
arXiv cs.GR details MotionPersona, a real-time locomotion controller that keeps performer-specific motion traits while retargeting across different bodies and styles. The system was trained on 48 performers and runs in …
Two2Four is a new human-to-quadruped puppeteering system that turns ordinary human motion into plausible animal animation. Built on a two-stage diffusion model trained only on quadruped motion, it aims to …
A new neural motion-blending system can interpolate animation across characters with different skeleton topologies, not just near-identical rigs. It pairs a semantic motion encoder with a diffusion decoder to reconstruct …
TopoCap tackles a real production pain point: retargeting motion from monocular video onto rigs that don’t share a human template. The paper claims zero-shot animation transfer across arbitrary skeletal topologies, …
AvatarMix tackles a real pain point in avatar outfit transfer: keeping identity and clothing intact without seam or intersection artifacts. It composes head and body from two high-fidelity Gaussian avatars, …
AnyAct turns monocular video of non-human characters into editable human motion, aiming to give animators a usable starting point instead of a full reconstruction. The method leans on sparse local …
A single rectified-flow model can now handle text-to-motion generation, semantic editing, and same-topology retargeting in one pass. The system conditions on both text and skeleton, then uses joint-level tokenization and …