İnsan hareketinin keyfi örgü modellerine örnek tabanlı aktarımı

Animation of mesh models can be accomplished in many ways, including character animation with skinned skeletons, deformable models, or physic-based simulation. Generating animations with all of these techniques is time consumingand laborious for novice users; however adapting already available wide-rangehuman motion capture data might simplify the process signi cantly. This thesispresents a method for retargeting human motion to arbitrary 3D mesh modelswith as little user interaction as possible. Traditional motion retargeting systemstry to preserve original motion as is, while satisfying several motion constraints.In our approach, we use a few pose-to-pose examples provided by the user toextract desired semantics behind retargeting process by not limiting the transferto be only literal. Hence, mesh models, which have dierent structures and/ormotion semantics from humanoid skeleton, become possible targets. Also considering mesh models which are widely available and without any additional structure (e.g. skeleton), our method does not require such a structure by providinga build-in surface-based deformation system. Since deformation for animationpurpose can require more than rigid behaviour, we augment existing rigid deformation approaches to provide volume preserving and cartoon-like deformation.For demonstrating results of our approach, we retarget several motion capturedata to three well-known models, and also investigate how automatic retargetingmethods developed considering humanoid models work on our models.Keywords: Mesh deformation, volume preservation, animation, motion retargeting