Kinematic Kitbashing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Minghao, Zordan, Victor, Andrews, Sheldon, Matusik, Wojciech, Agrawala, Maneesh, Liu, Hsueh-Ti Derek
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917461754904576
author Guo, Minghao
Zordan, Victor
Andrews, Sheldon
Matusik, Wojciech
Agrawala, Maneesh
Liu, Hsueh-Ti Derek
author_facet Guo, Minghao
Zordan, Victor
Andrews, Sheldon
Matusik, Wojciech
Agrawala, Maneesh
Liu, Hsueh-Ti Derek
contents We introduce Kinematic Kitbashing, an optimization framework that synthesizes articulated 3D objects by assembling reusable parts conditioned on an abstract kinematic graph. Given the graph and a library of articulated parts, our method optimizes per-part similarity transformations that place, orient, and scale each component into a coherent articulated object; optional graph edits further enable novel assemblies beyond the prescribed connectivity. Central to our method is an exemplar-based analogy for part placement: each reused component is paired with a single source asset that exemplifies how it attaches to its parent. We capture this attachment context using vector distance fields and measure consistency by integrating the matching error over the joint's full motion range. This yields a kinematics-aware attachment energy that favors placements that preserve the exemplar's local attachment neighborhood throughout articulation. To incorporate task-level functionality, we use this attachment energy as a prior in an annealed Langevin sampling framework, enabling gradient-free optimization of black-box functionality objectives. We demonstrate the versatility of kinematic kitbashing across diverse applications, including instantiating kinematic graphs from user-selected or automatically retrieved parts, synthesizing assemblies with user-defined functionality, and re-targeting articulations via graph edits.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13048
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Kinematic Kitbashing
Guo, Minghao
Zordan, Victor
Andrews, Sheldon
Matusik, Wojciech
Agrawala, Maneesh
Liu, Hsueh-Ti Derek
Robotics
Graphics
I.3.6
We introduce Kinematic Kitbashing, an optimization framework that synthesizes articulated 3D objects by assembling reusable parts conditioned on an abstract kinematic graph. Given the graph and a library of articulated parts, our method optimizes per-part similarity transformations that place, orient, and scale each component into a coherent articulated object; optional graph edits further enable novel assemblies beyond the prescribed connectivity. Central to our method is an exemplar-based analogy for part placement: each reused component is paired with a single source asset that exemplifies how it attaches to its parent. We capture this attachment context using vector distance fields and measure consistency by integrating the matching error over the joint's full motion range. This yields a kinematics-aware attachment energy that favors placements that preserve the exemplar's local attachment neighborhood throughout articulation. To incorporate task-level functionality, we use this attachment energy as a prior in an annealed Langevin sampling framework, enabling gradient-free optimization of black-box functionality objectives. We demonstrate the versatility of kinematic kitbashing across diverse applications, including instantiating kinematic graphs from user-selected or automatically retrieved parts, synthesizing assemblies with user-defined functionality, and re-targeting articulations via graph edits.
title Kinematic Kitbashing
topic Robotics
Graphics
I.3.6
url https://arxiv.org/abs/2510.13048