Learning to Assemble Geometric Shapes
This work addresses a combinatorial assembly problem in science and engineering, but it is incremental as it builds on prior limited cases by extending to more complex scenarios.
The paper tackles the challenging problem of assembling textureless fragments of arbitrary shapes with indistinctive junctions, introducing a learning-based approach that demonstrates effectiveness across various scenarios including abnormal fragments, different fragment counts, and rotation discretizations.
Assembling parts into an object is a combinatorial problem that arises in a variety of contexts in the real world and involves numerous applications in science and engineering. Previous related work tackles limited cases with identical unit parts or jigsaw-style parts of textured shapes, which greatly mitigate combinatorial challenges of the problem. In this work, we introduce the more challenging problem of shape assembly, which involves textureless fragments of arbitrary shapes with indistinctive junctions, and then propose a learning-based approach to solving it. We demonstrate the effectiveness on shape assembly tasks with various scenarios, including the ones with abnormal fragments (e.g., missing and distorted), the different number of fragments, and different rotation discretization.