Seg Struct: The Interplay Between Part Segmentation and Structure Inference for 3D Shape Parsing

11/01/2022
by   Jeonghyun Kim, et al.
0

We propose Seg Struct, a supervised learning framework leveraging the interplay between part segmentation and structure inference and demonstrating their synergy in an integrated framework. Both part segmentation and structure inference have been extensively studied in the recent deep learning literature, while the supervisions used for each task have not been fully exploited to assist the other task. Namely, structure inference has been typically conducted with an autoencoder that does not leverage the point-to-part associations. Also, segmentation has been mostly performed without structural priors that tell the plausibility of the output segments. We present how these two tasks can be best combined while fully utilizing supervision to improve performance. Our framework first decomposes a raw input shape into part segments using an off-the-shelf algorithm, whose outputs are then mapped to nodes in a part hierarchy, establishing point-to-part associations. Following this, ours predicts the structural information, e.g., part bounding boxes and part relationships. Lastly, the segmentation is rectified by examining the confusion of part boundaries using the structure-based part features. Our experimental results based on the StructureNet and PartNet demonstrate that the interplay between the two tasks results in remarkable improvements in both tasks: 27.91 in structure inference and 0.5

READ FULL TEXT

page 6

page 16

page 18

page 19

page 20

page 21

page 22

page 23

research
04/10/2023

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 o...
research
07/14/2020

Deep Heterogeneous Autoencoder for Subspace Clustering of Sequential Data

We propose an unsupervised learning approach using a convolutional and f...
research
06/09/2018

Cell Detection with Star-convex Polygons

Automatic detection and segmentation of cells and nuclei in microscopy i...
research
03/25/2018

Text Segmentation as a Supervised Learning Task

Text segmentation, the task of dividing a document into contiguous segme...
research
10/08/2021

Meta-Learning 3D Shape Segmentation Functions

Learning robust 3D shape segmentation functions with deep neural network...
research
04/18/2020

Finding Berries: Segmentation and Counting of Cranberries using Point Supervision and Shape Priors

Precision agriculture has become a key factor for increasing crop yields...
research
11/26/2015

Iterative Instance Segmentation

Existing methods for pixel-wise labelling tasks generally disregard the ...

Please sign up or login with your details

Forgot password? Click here to reset