# PlaneSegNet: Fast and Robust Plane Estimation Using a Single-stage Instance Segmentation CNN

arXiv: https://arxiv.org/abs/2103.15428 · HTML: https://mlsanity.com/paper/2103.15428/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 29 Mar 2021.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [Dilated Residual Networks](https://mlsanity.com/paper/1705.09914/) (2017)
- [Conditional Random Fields as Recurrent Neural Networks](https://mlsanity.com/paper/1502.03240/) (2015)
- [Fully Convolutional Instance-aware Semantic Segmentation](https://mlsanity.com/paper/1611.07709/) (2016)
- [PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image](https://mlsanity.com/paper/1812.04072/) (2018)
- [YOLACT++: Better Real-time Instance Segmentation](https://mlsanity.com/paper/1912.06218/) (2019)
- [PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image](https://mlsanity.com/paper/1804.06278/) (2018)
- [Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding](https://mlsanity.com/paper/1902.09777/) (2019)
- [AugFPN: Improving Multi-scale Feature Learning for Object Detection](https://mlsanity.com/paper/1912.05384/) (2019)
- [Monocular Object and Plane SLAM in Structured Environments](https://mlsanity.com/paper/1809.03415/) (2018)
- [Structure Aware SLAM using Quadrics and Planes](https://mlsanity.com/paper/1804.09111/) (2018)
- [FeatureNMS: Non-Maximum Suppression by Learning Feature Embeddings](https://mlsanity.com/paper/2002.07662/) (2020)
- [Ground Plane Polling for 6DoF Pose Estimation of Objects on the Road](https://mlsanity.com/paper/1811.06666/) (2018)

## Built on by (most cited first, 7 of 7)

- [Structure PLP-SLAM: Efficient Sparse Mapping and Localization using Point, Line and Plane for Monocular, RGB-D and Stereo Cameras](https://mlsanity.com/paper/2207.06058/) (2022)
- [PlaneRecNet: Multi-Task Learning with Cross-Task Consistency for Piece-Wise Plane Detection and Reconstruction from a Single RGB Image](https://mlsanity.com/paper/2110.11219/) (2021)
- [Visual SLAM with Graph-Cut Optimized Multi-Plane Reconstruction](https://mlsanity.com/paper/2108.04281/) (2021)
- [X-PDNet: Accurate Joint Plane Instance Segmentation and Monocular Depth Estimation with Cross-Task Distillation and Boundary Correction](https://mlsanity.com/paper/2309.08424/) (2023)
- [PlanarGS: High-Fidelity Indoor 3D Gaussian Splatting Guided by Vision-Language Planar Priors](https://mlsanity.com/paper/2510.23930/) (2025)
- [Multi-task Planar Reconstruction with Feature Warping Guidance](https://mlsanity.com/paper/2311.14981/) (2023)
- [PlaneSAM: Multimodal Plane Instance Segmentation Using the Segment Anything Model](https://mlsanity.com/paper/2410.16545/) (2024)

## Abstract (arXiv)

Instance segmentation of planar regions in indoor scenes benefits visual SLAM and other applications such as augmented reality (AR) where scene understanding is required. Existing methods built upon two-stage frameworks show satisfactory accuracy but are limited by low frame rates. In this work, we propose a real-time deep neural architecture that estimates piece-wise planar regions from a single RGB image. Our model employs a variant of a fast single-stage CNN architecture to segment plane instances. Considering the particularity of the target detected, we propose Fast Feature Non-maximum Suppression (FF-NMS) to reduce the suppression errors resulted from overlapping bounding boxes of planes. We also utilize a Residual Feature Augmentation module in the Feature Pyramid Network (FPN). Our method achieves significantly higher frame-rates and comparable segmentation accuracy against two-stage methods. We automatically label over 70,000 images as ground truth from the Stanford 2D-3D-Semantics dataset. Moreover, we incorporate our method with a state-of-the-art planar SLAM and validate its benefits.