Combinatorial 3D Shape Generation via Sequential Assembly
This work addresses a domain-specific problem in robotics and 3D vision by providing a practical blueprint for constructing target shapes, though it appears incremental as it builds on existing sequential assembly concepts with a novel optimization approach.
The paper tackles the problem of generating combinatorial 3D shapes via sequential assembly, where greedy methods fail due to the huge number of feasible combinations, and proposes a framework using Bayesian optimization to efficiently explore constrained regions, resulting in successful generation of shapes and more realistic simulation of assembly processes.
Sequential assembly with geometric primitives has drawn attention in robotics and 3D vision since it yields a practical blueprint to construct a target shape. However, due to its combinatorial property, a greedy method falls short of generating a sequence of volumetric primitives. To alleviate this consequence induced by a huge number of feasible combinations, we propose a combinatorial 3D shape generation framework. The proposed framework reflects an important aspect of human generation processes in real life -- we often create a 3D shape by sequentially assembling unit primitives with geometric constraints. To find the desired combination regarding combination evaluations, we adopt Bayesian optimization, which is able to exploit and explore efficiently the feasible regions constrained by the current primitive placements. An evaluation function conveys global structure guidance for an assembly process and stability in terms of gravity and external forces simultaneously. Experimental results demonstrate that our method successfully generates combinatorial 3D shapes and simulates more realistic generation processes. We also introduce a new dataset for combinatorial 3D shape generation. All the codes are available at \url{https://github.com/POSTECH-CVLab/Combinatorial-3D-Shape-Generation}.