Contrastive Boundary Learning for Point Cloud Segmentation
- URL: http://arxiv.org/abs/2203.05272v2
- Date: Fri, 11 Mar 2022 09:39:52 GMT
- Title: Contrastive Boundary Learning for Point Cloud Segmentation
- Authors: Liyao Tang, Yibing Zhan, Zhe Chen, Baosheng Yu, Dacheng Tao
- Abstract summary: We propose a novel contrastive boundary learning framework for point cloud segmentation.
We experimentally show that CBL consistently improves different baselines and assists them to achieve compelling performance on boundaries.
- Score: 81.7289734276872
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Point cloud segmentation is fundamental in understanding 3D environments.
However, current 3D point cloud segmentation methods usually perform poorly on
scene boundaries, which degenerates the overall segmentation performance. In
this paper, we focus on the segmentation of scene boundaries. Accordingly, we
first explore metrics to evaluate the segmentation performance on scene
boundaries. To address the unsatisfactory performance on boundaries, we then
propose a novel contrastive boundary learning (CBL) framework for point cloud
segmentation. Specifically, the proposed CBL enhances feature discrimination
between points across boundaries by contrasting their representations with the
assistance of scene contexts at multiple scales. By applying CBL on three
different baseline methods, we experimentally show that CBL consistently
improves different baselines and assists them to achieve compelling performance
on boundaries, as well as the overall performance, eg in mIoU. The experimental
results demonstrate the effectiveness of our method and the importance of
boundaries for 3D point cloud segmentation. Code and model will be made
publicly available at https://github.com/LiyaoTang/contrastBoundary.
Related papers
- Temporal Action Localization with Enhanced Instant Discriminability [66.76095239972094]
Temporal action detection (TAD) aims to detect all action boundaries and their corresponding categories in an untrimmed video.
We propose a one-stage framework named TriDet to resolve imprecise predictions of action boundaries by existing methods.
Experimental results demonstrate the robustness of TriDet and its state-of-the-art performance on multiple TAD datasets.
arXiv Detail & Related papers (2023-09-11T16:17:50Z) - CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud
Semantic Segmentation [60.0893353960514]
We study the task of weakly-supervised point cloud semantic segmentation with sparse annotations.
We propose a Contextual Point Cloud Modeling ( CPCM) method that consists of two parts: a region-wise masking (RegionMask) strategy and a contextual masked training (CMT) method.
arXiv Detail & Related papers (2023-07-19T04:41:18Z) - FreePoint: Unsupervised Point Cloud Instance Segmentation [72.64540130803687]
We propose FreePoint, for underexplored unsupervised class-agnostic instance segmentation on point clouds.
We represent point features by combining coordinates, colors, and self-supervised deep features.
Based on the point features, we segment point clouds into coarse instance masks as pseudo labels, which are used to train a point cloud instance segmentation model.
arXiv Detail & Related papers (2023-05-11T16:56:26Z) - Push-the-Boundary: Boundary-aware Feature Propagation for Semantic
Segmentation of 3D Point Clouds [0.5249805590164901]
We propose a boundary-aware feature propagation mechanism to improve semantic segmentation near object boundaries.
With one shared encoder, our network outputs (i) boundary localization, (ii) prediction of directions pointing to the object's interior, and (iii) semantic segmentation, in three parallel streams.
Our proposed approach yields consistent improvements by reducing boundary errors.
arXiv Detail & Related papers (2022-12-23T15:42:01Z) - PNM: Pixel Null Model for General Image Segmentation [17.971090313814447]
We present a prior model that weights each pixel according to its probability of being correctly classified by a random segmenter.
Experiments on semantic, instance, and panoptic segmentation tasks over three datasets confirm that PNM consistently improves the segmentation quality.
We propose a new metric, textitPNM IoU, which perceives the boundary sharpness and better reflects the model segmentation performance in error-prone regions.
arXiv Detail & Related papers (2022-03-13T15:17:41Z) - Boundary Guided Context Aggregation for Semantic Segmentation [23.709865471981313]
We exploit boundary as a significant guidance for context aggregation to promote the overall semantic understanding of an image.
We conduct extensive experiments on the Cityscapes and ADE20K databases, and comparable results are achieved with the state-of-the-art methods.
arXiv Detail & Related papers (2021-10-27T17:04:38Z) - Unsupervised Representation Learning for 3D Point Cloud Data [66.92077180228634]
We propose a simple yet effective approach for unsupervised point cloud learning.
In particular, we identify a very useful transformation which generates a good contrastive version of an original point cloud.
We conduct experiments on three downstream tasks which are 3D object classification, shape part segmentation and scene segmentation.
arXiv Detail & Related papers (2021-10-13T10:52:45Z) - LRGNet: Learnable Region Growing for Class-Agnostic Point Cloud
Segmentation [19.915593390338337]
This research proposes a learnable region growing method for class-agnostic point cloud segmentation.
The proposed method is able to segment any class of objects using a single deep neural network without any assumptions about their shapes and sizes.
arXiv Detail & Related papers (2021-03-16T15:58:01Z) - Boundary-Aware Geometric Encoding for Semantic Segmentation of Point
Clouds [45.270215729464056]
Boundary information plays a significant role in 2D image segmentation, while usually being ignored in 3D point cloud segmentation.
We propose a Boundary Prediction Module (BPM) to predict boundary points.
Based on the predicted boundary, a boundary-aware Geometric.
GEM is designed to encode geometric information and aggregate features with discrimination in a neighborhood.
arXiv Detail & Related papers (2021-01-07T05:38:19Z) - Contrastive Rendering for Ultrasound Image Segmentation [59.23915581079123]
The lack of sharp boundaries in US images remains an inherent challenge for segmentation.
We propose a novel and effective framework to improve boundary estimation in US images.
Our proposed method outperforms state-of-the-art methods and has the potential to be used in clinical practice.
arXiv Detail & Related papers (2020-10-10T07:14:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.