SHRED: 3D Shape Region Decomposition with Learned Local Operations

2022/06/07 by R. Kenny Jones, Jones, R. Kenny, Aalia Habib +3 · 1 citation
Engineering · Earth and Planetary Sciences · Computer Science · #3D Shape Modeling and Analysis #3D Surveying and Cultural Heritage #Advanced Neural Network Applications

paper · pdf · doi:10.48550/arxiv.2206.03480

Abstract

We present SHRED, a method for 3D SHape REgion Decomposition. SHRED takes a 3D point cloud as input and uses learned local operations to produce a segmentation that approximates fine-grained part instances. We endow SHRED with three decomposition operations: splitting regions, fixing the boundaries between regions, and merging regions together. Modules are trained independently and locally, allowing SHRED to generate high-quality segmentations for categories not seen during training. We train and evaluate SHRED with fine-grained segmentations from PartNet; using its merge-threshold hyperparameter, we show that SHRED produces segmentations that better respect ground-truth annotations compared with baseline methods, at any desired decomposition granularity. Finally, we demonstrate that SHRED is useful for downstream applications, out-performing all baselines on zero-shot fine-grained part instance segmentation and few-shot fine-grained semantic segmentation when combined with methods that learn to label shape regions.

Cited by

• ASIA: Adaptive 3D Segmentation using Few Image Annotations

Related

• Learning Fine-Grained Segmentation of 3D Shapes without Part Labels
• PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyond
• Learning Point Embeddings from Shape Repositories for Few-Shot\n Segmentation
• Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories
• The Neurally-Guided Shape Parser: Grammar-based Labeling of 3D Shape Regions with Approximate Inference