3D Bird’s-Eye-View Instance Segmentation

Elich, Cathrin; Engelmann, Francis; Schult, Jonas; Kontogianni, Theodora; Leibe, Bastian

doi:10.1007/978-3-030-33676-9_4

Cited by 52 publications

(36 citation statements)

References 29 publications

(63 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Region proposal methods 3D-BoNet [64], GSPN (R-PointNet) [65], PanopticFusion [66], LIDARSeg [67], 3DSIS [68], GICN [69] Region proposal free methods SGPN [70], MASC [71], Discriminative embeddings [72], MTML [73], Dynamic Region Growing [74], Clus-terNet [75], PointGroup [76], 3D-BEVIS [77], 3D MPA [78], MT-PNet [79], ASIS [80], JSNet [81]…”

Section: Categories Representative Methodsmentioning

confidence: 99%

“…To implement instance segmentation over complete 3D scans, Elich et al [77] brought up 3D-BEVIS which is a 2D-3D bird's eye view framework which learns global consistent instances features from a u-shaped fully convolution network. The point clouds features are mutually predicted by a graph neural network.…”

Section: Region Proposal Free Methodsmentioning

confidence: 99%

“…For the proposal free methods, there exist fundamental limitations such as for scenes where various occluded objects are not well visible. As an example, 3D-BEVIS [77] is able to learn global instance features which are consistent over a full scene.…”

Section: Performance On Scenes Variationsmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning Methods Applied to 3D Point Clouds Based Instance Segmentation: A Review

Burume¹,

Du²

2021

Preprint

View full text Add to dashboard Cite

Beyond semantic segmentation,3D instance segmentation(a process to delineate objects of interest and also classifying the objects into a set of categories) is gaining more and more interest among researchers since numerous computer vision applications need accurate segmentation processes(autonomous driving, indoor navigation, and even virtual or augmented reality systems…) This paper gives an overview and a technical comparison of the existing deep learning architectures in handling unstructured Euclidean data for the rapidly developing 3D instance segmentation. First, the authors divide the 3D point clouds based instance segmentation techniques into two major categories which are proposal based methods and proposal free methods. Then, they also introduce and compare the most used datasets with regard to 3D instance segmentation. Furthermore, they compare and analyze these techniques performance (speed, accuracy, response to noise…). Finally, this paper provides a review of the possible future directions of deep learning for 3D sensor-based information and provides insight into the most promising areas for prospective research.

show abstract

Section: Categories Representative Methodsmentioning

confidence: 99%

Section: Region Proposal Free Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Methods Applied to 3D Point Clouds Based Instance Segmentation: A Review

Burume¹,

Du²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Based on the great success achieved in recent years [1,2,5,6,[9][10][11][12][13][14][19][20][21] for each single task of semantic and instance segmentation in 3D point clouds, joint learning methods for both tasks [14][15][16] have opened up a new effective way to explore the 3D scene segmentation, which can not only improve the performance but also promote further development. However, there still remain some challenges in the joint segmentation tasks especially for instance segmentation.…”

Section: Introductionmentioning

confidence: 99%

SASO: Joint 3D semantic‐instance segmentation via multi‐scale semantic association and salient point clustering optimization

Tan

Chen

Wang

et al. 2021

IET Computer Vision

View full text Add to dashboard Cite

Jointly performing semantic and instance segmentation of 3D point cloud remains a challenging task. In this work, a novel framework called joint 3D semantic-instance segmentation via multi-scale Semantic Association and Salient point clustering Optimization was proposed to tackle this problem. Inspired by the inherent correlation among objects in semantic space, a Multi-scale Semantic Association (MSA) module to explore the constructive effect of the context information for semantic segmentation is designed. For instance, segmentation, different from previous works utilising clustering only in inference procedure, a Salient Point Clustering Optimization (SPCO) module is put forward to introduce the clustering algorithm into the training phase, which impels the network to focus on points that are difficult to be distinguished. Furthermore, affected by the inherent structure of indoor scenes, the problem of uneven distribution of categories has rarely been considered in the previous work, but it significantly limits the performance of 3D scene perception. To address the issue, an adaptive Water Filling Sampling (WFS) algorithm to balance the category distribution of training data is presented. Extensive experiments on a variety of changing datasets show that the authors' method outperforms the state-of-theart methods in both tasks of semantic segmentation and instance segmentation.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

“…In recent years, many deep learning based methods [1][2][3][4][5][6][7][8][9][10][11][12] for point cloud instance segmentation have emerged and boosted the performance in a large margin. These methods could be divided into two categories.…”

Section: Introductionmentioning

confidence: 99%

Spcr: semi-supervised point cloud instance segmentation with perturbation consistency regularization

Liao

Zhu

Chen

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Point cloud instance segmentation is steadily improving with the development of deep learning. However, current progress is hindered by the expensive cost of collecting dense point cloud labels. To this end, we propose the first semi-supervised point cloud instance segmentation architecture, which is called semi-supervised point cloud instance segmentation with perturbation consistency regularization (SPCR). It is capable to alleviate the data-hungry bottleneck of existing strongly supervised methods. Specifically, SPCR enforces an invariance of the predictions over different perturbations applied to the input point clouds. We firstly introduce various perturbation schemes on inputs to force the network to be robust and easily generalized to the unseen and unlabeled data. Further, perturbation consistency regularization is then conducted on predicted instance masks from various transformed inputs to provide self-supervision for network learning. Extensive experiments on the challenging ScanNet v2 dataset demonstrate our method can achieve competitive performance compared with the state-of-the-art of fully supervised methods.

show abstract

3D Bird’s-Eye-View Instance Segmentation

Cited by 52 publications

References 29 publications

Deep Learning Methods Applied to 3D Point Clouds Based Instance Segmentation: A Review

Deep Learning Methods Applied to 3D Point Clouds Based Instance Segmentation: A Review

SASO: Joint 3D semantic‐instance segmentation via multi‐scale semantic association and salient point clustering optimization

Spcr: semi-supervised point cloud instance segmentation with perturbation consistency regularization

Contact Info

Product

Resources

About