English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Achieving tight bounding boxes of a shape while guaranteeing completeboundness is an essential task for efficient geometric operations andunsupervised semantic part detection. But previous methods fail to achieve bothfull coverage and tightness. Neural-network-based methods are not suitable forthese goals due to the non-differentiability of the objective, while classiciterative search methods suffer from their sensitivity to the initialization.We propose a novel framework for finding a set of tight bounding boxes of a 3Dshape via over-segmentation and iterative merging and refinement. Our resultshows that utilizing effective search methods with appropriate objectives isthe key to producing bounding boxes with both properties. We employ an existingpre-segmentation to split the shape and obtain over-segmentation. Then, weapply hierarchical merging with our novel tightness-aware merging and stoppingcriteria. To overcome the sensitivity to the initialization, we also defineactions 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 3Dshapes, we demonstrate full coverage, tightness, and an adequate number ofbounding boxes of our method without requiring any training data orsupervision. It thus can be applied to various downstream tasks in computervision and graphics.

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