Split, Merge, and Refine: Fitting Tight Bounding Boxes via Over-Segmentation and Iterative Search
Achieving tight bounding boxes of a shape while guaranteeing 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, while classic iterative search methods suffer from their sensitivity to the initialization. We propose a novel framework for finding a set of tight bounding boxes of a 3D shape via over-segmentation and iterative merging and refinement. Our result shows that utilizing effective search methods with appropriate objectives is the key to producing bounding boxes with both properties. We employ an existing pre-segmentation to split the shape and obtain over-segmentation. Then, we apply hierarchical merging with our novel tightness-aware merging and stopping criteria. To overcome the sensitivity to the initialization, we also define actions to refine the bounding box parameters in an Markov Decision Process (MDP) setup with a soft reward function promoting a wider exploration. Lastly, we further improve the refinement step with Monte Carlo Tree Search (MCTS) based multi-action space exploration. By thoughtful evaluation on diverse 3D shapes, we demonstrate full coverage, tightness, and an adequate number of bounding boxes of our method without requiring any training data or supervision. It thus can be applied to various downstream tasks in computer vision and graphics.
Code (0)
등록된 구현이 없습니다.
Tasks
SegmentationSemantic Part DetectionSensitivityMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Multi-Stage Reinforcement Learning For Object Detection
We present a reinforcement learning approach for detecting objects within an image. Our approach performs a step-wise deformation of a bounding box with the goal of tightly framing the object. It uses a hierarchical tree…
Objectobject-detectionObject Detectionreinforcement-learning+2BoxSplitGen: A Generative Model for 3D Part Bounding Boxes in Varying Granularity
Human creativity follows a perceptual process, moving from abstract ideas to finer details during creation. While 3D generative models have advanced dramatically, models specifically designed to assist human imagination …
Adaptive Uncertainty Quantification for Generative AI
This work is concerned with conformal prediction in contemporary applications (including generative AI) where a black-box model has been trained on data that are not accessible to the user. Mirroring split-conformal infe…
Conformal PredictionUncertainty QuantificationFairness Overfitting in Machine Learning: An Information-Theoretic Perspective
Despite substantial progress in promoting fairness in high-stake applications using machine learning models, existing methods often modify the training process, such as through regularizers or other interventions, but la…
FairnessGeneralization BoundsMedical image segmentation with imperfect 3D bounding boxes
The development of high quality medical image segmentation algorithms depends on the availability of large datasets with pixel-level labels. The challenges of collecting such datasets, especially in case of 3D volumes, m…
Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation+1