Deep Learning Based 3D Segmentation: A Survey

TL;DR

This survey comprehensively reviews recent deep learning methods for 3D segmentation across various data modalities and applications, analyzing their strengths, limitations, and benchmark performances to guide future research.

Contribution

It provides an in-depth, up-to-date survey of over 220 deep learning-based 3D segmentation methods across all data modalities and application domains.

Findings

Deep learning significantly outperforms traditional methods in 3D segmentation.

Benchmark datasets reveal strengths and limitations of current approaches.

The survey highlights promising future research directions.

Abstract

3D segmentation is a fundamental and challenging problem in computer vision with applications in autonomous driving and robotics. It has received significant attention from the computer vision, graphics and machine learning communities. Conventional methods for 3D segmentation, based on hand-crafted features and machine learning classifiers, lack generalization ability. Driven by their success in 2D computer vision, deep learning techniques have recently become the tool of choice for 3D segmentation tasks. This has led to an influx of many methods in the literature that have been evaluated on different benchmark datasets. Whereas survey papers on RGB-D and point cloud segmentation exist, there is a lack of a recent in-depth survey that covers all 3D data modalities and application domains. This paper fills the gap and comprehensively surveys the recent progress in deep learning-based 3D segmentation techniques. We cover over 220 works from the last six years, analyze their strengths and limitations, and discuss their competitive results on benchmark datasets. The survey provides a summary of the most commonly used pipelines and finally highlights promising research directions for the future.