Split, Merge, and Refine: Fitting Tight Bounding Boxes via Learned Over-Segmentation and Iterative Search

We present a novel framework for finding a set of tight bounding boxes of a 3D shape via neural-network-based over-segmentation and iterative merging and refinement. Achieving tight bounding boxes of a shape while guaranteeing the complete boundness is an essential task for efficient geometric operations and unsupervised semantic part detection, but previous methods fail to achieve both full coverage and tightness. Neural-network-based methods are not suitable for these goals due to the non-differentiability of the objective, and also classic iterative search methods suffer from their sensitivity to the initialization. We demonstrate that the best integration of the learning-based and iterative search methods can achieve the bounding boxes with both properties. We employ an existing unsupervised segmentation network to \textbf{split} the shape and obtain over-segmentation. Then, we apply hierarchical \textbf{merging} with our novel tightness-aware merging and stopping criteria. To overcome the sensitivity to the initialization, we also \textbf{refine} the bounding box parameters in a game setup with a soft reward function promoting a wider exploration. Lastly, we further improve the bounding boxes with a MCTS-based multi-action space exploration. Our experimental results demonstrate the full coverage, tightness, and the adequate number of bounding boxes of our method.