4 papers
Kinematic Kitbashing
Minghao Guo, Victor Zordan, Sheldon Andrews +3
We introduce Kinematic Kitbashing, an optimization framework that synthesizes articulated 3D objects by assembling reusable parts conditioned on an abstract kinematic graph. Given…
Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenization
Kangle Deng, Hsueh-Ti Derek Liu, Yiheng Zhu +7
Many 3D generative models rely on variational autoencoders (VAEs) to learn compact shape representations. However, existing methods encode all shapes into a fixed-size token, disre…
GEOPARD: Geometric Pretraining for Articulation Prediction in 3D Shapes
Pradyumn Goyal, Dmitry Petrov, Sheldon Andrews +3
We present GEOPARD, a transformer-based architecture for predicting articulation from a single static snapshot of a 3D shape. The key idea of our method is a pretraining strategy t…
Actuators à La Mode: Modal Actuations for Soft Body Locomotion
Otman Benchekroun, Kaixiang Xie, Hsueh-Ti Derek Liu +3
Traditional character animation specializes in characters with a rigidly articulated skeleton and a bipedal/quadripedal morphology. This assumption simplifies many aspects for desi…