3D Shape Segmentation with Projective Convolutional Networks

Citations Over TimeTop 1% of 2017 papers

Abstract

This paper introduces a deep architecture for segmenting 3D objects into their labeled semantic parts. Our architecture combines image-based Fully Convolutional Networks (FCNs) and surface-based Conditional Random Fields (CRFs) to yield coherent segmentations of 3D shapes. The image-based FCNs are used for efficient view-based reasoning about 3D object parts. Through a special projection layer, FCN outputs are effectively aggregated across multiple views and scales, then are projected onto the 3D object surfaces. Finally, a surface-based CRF combines the projected outputs with geometric consistency cues to yield coherent segmentations. The whole architecture (multi-view FCNs and CRF) is trained end-to-end. Our approach significantly outperforms the existing state-of-the-art methods in the currently largest segmentation benchmark (ShapeNet). Finally, we demonstrate promising segmentation results on noisy 3D shapes acquired from consumer-grade depth cameras.

Related Papers

• → Analyzing Semantic Segmentation Using Hybrid Human-Machine CRFs(2013)36 cited
• → CRF-Based Brain Tumor Segmentation: Alleviating the Shrinking Bias(2016)18 cited
• → Deep Neural Networks for Surface Segmentation Meet Conditional Random Fields(2019)6 cited
• 3-D Surface Segmentation Meets Conditional Random Fields.(2019)