# 3D Instance Segmentation Using Deep Learning on RGB-D Indoor Data

arXiv: https://arxiv.org/abs/2406.14581 · HTML: https://mlsanity.com/paper/2406.14581/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 31 references that are in the map.
- First posted on arXiv 19 Jun 2024.

## Builds on (most cited first, 17 of 17)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Frustum PointNets for 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1711.08488/) (2017)
- [PointRend: Image Segmentation as Rendering](https://mlsanity.com/paper/1912.08193/) (2019)
- [Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics](https://mlsanity.com/paper/1703.09312/) (2017)
- [GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud](https://mlsanity.com/paper/1812.03320/) (2018)
- [Vehicle Detection from 3D Lidar Using Fully Convolutional Network](https://mlsanity.com/paper/1608.07916/) (2016)
- [Learning to Segment Object Candidates](https://mlsanity.com/paper/1506.06204/) (2015)
- [DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution](https://mlsanity.com/paper/2011.13328/) (2020)
- [Recurrent Pixel Embedding for Instance Grouping](https://mlsanity.com/paper/1712.08273/) (2017)
- [Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation](https://mlsanity.com/paper/2004.02186/) (2020)
- [Expandable YOLO: 3D Object Detection from RGB-D Images](https://mlsanity.com/paper/2006.14837/) (2020)

## Built on by (most cited first, 2 of 2)

- [Geometry-Aware Sparse Depth Sampling for High-Fidelity RGB-D Depth Completion in Robotic Systems](https://mlsanity.com/paper/2512.08229/) (2025)
- [Leveraging Deep Learning for Object and Position Recognition of Load Carriers for Autonomous Logistics Vehicles](https://mlsanity.com/paper/2606.16042/) (2026)

## Abstract (arXiv)

3D object recognition is a challenging task for intelligent and robot systems in industrial and home indoor environments. It is critical for such systems to recognize and segment the 3D object instances that they encounter on a frequent basis. The computer vision, graphics, and machine learning fields have all given it a lot of attention. Traditionally, 3D segmentation was done with hand-crafted features and designed approaches that did not achieve acceptable performance and could not be generalized to large-scale data. Deep learning approaches have lately become the preferred method for 3D segmentation challenges by their great success in 2D computer vision. However, the task of instance segmentation is currently less explored. In this paper, we propose a novel approach for efficient 3D instance segmentation using red green blue and depth (RGB-D) data based on deep learning. The 2D region based convolutional neural networks (Mask R-CNN) deep learning model with point based rending module is adapted to integrate with depth information to recognize and segment 3D instances of objects. In order to generate 3D point cloud coordinates (x, y, z), segmented 2D pixels (u, v) of recognized object regions in the RGB image are merged into (u, v) points of the depth image. Moreover, we conducted an experiment and analysis to compare our proposed method from various points of view and distances. The experimentation shows the proposed 3D object recognition and instance segmentation are sufficiently beneficial to support object handling in robotic and intelligent systems.