Get Started
Home
Topics
Search
Library
Research questionHow can we accurately pose AI-generated 3D characters with fused geometry and changing topology?AI-generated character meshes may contain fused parts and inconsistent topology, making conventional skinning unreliable. The resulting deformations can fail to conform to target poses.
AI
Computer Vision
Machine Learning
Research Paper
Technology
Latest papersRecent research connected to this question, newest first.Make-It-Poseable: Feed-forward Latent Posing Model for 3D CharactersApplies to Make-It-Poseable, a feed-forward, skinning-free latent posing framework for 3D characters that reports improved posing quality over existing baselines. Its generalization to quadrupeds is supported qualitatively, and part replacement and refinement are described as authoring applications.research paper · Sep 2, 2026
Related questions
How can human motion be retargeted across different humanoid morphologies without hand-crafted mappings or losing pose detail?How can online 3D reconstruction maintain globally consistent poses and geometry over long video sequences?How can we generate text-guided motion for arbitrary 3D skeletons without per-skeleton adaptation or reference motions?How can we generate scalable, photorealistic labeled data for monocular 3D human mesh estimation?