Open AccessPosted Content
Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning.
TL;DR: The proposed spatial semantic embedding network (SSEN), a simple, yet efficient algorithm for 3D instance segmentation using deep metric learning, is presented, which is compact and fast with competitive performance, maintaining scalability on large scenes with high resolution voxels.
read more
Abstract: We propose spatial semantic embedding network (SSEN), a simple, yet efficient algorithm for 3D instance segmentation using deep metric learning The raw 3D reconstruction of an indoor environment suffers from occlusions, noise, and is produced without any meaningful distinction between individual entities For high-level intelligent tasks from a large scale scene, 3D instance segmentation recognizes individual instances of objects We approach the instance segmentation by simply learning the correct embedding space that maps individual instances of objects into distinct clusters that reflect both spatial and semantic information Unlike previous approaches that require complex pre-processing or post-processing, our implementation is compact and fast with competitive performance, maintaining scalability on large scenes with high resolution voxels We demonstrate the state-of-the-art performance of our algorithm in the ScanNet 3D instance segmentation benchmark on AP score
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Density-based clustering based on hierarchical density estimates
Ricardo J. G. B. Campello,Davoud Moulavi,Joerg Sander +2 more
- 01 Jan 2013
TL;DR: In this article, the authors proposed a hierarchical density-based hierarchical clustering method, which provides a clustering hierarchy from which a simplified tree of significant clusters can be constructed, and demonstrated that their approach outperforms the current, state-of-the-art, densitybased clustering methods.
556
•Posted Content
STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
TL;DR: A novel approach that segments and tracks instances across space and time in a single stage and is trained end-to-end to learn spatio-temporal embeddings as well as parameters required to cluster pixels belonging to a specific objectinstance over an entire video clip is proposed.
•Proceedings Article
Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks.
Zhihao Liang,Zhihao Li,Songcen Xu,Mingkui Tan,Kui Jia +4 more
- 17 Aug 2021
TL;DR: SSTNet as mentioned in this paper proposes an end-to-end solution of Semantic Superpoint Tree Network (SSTnet) for proposing object instances from scene points, which is constructed based on the learned semantic features of superpoints, and which will be traversed and split at intermediate tree nodes for proposals of object instances.
•Posted Content
LiDAR-based Panoptic Segmentation via Dynamic Shifting Network.
TL;DR: This work proposes the Dynamic Shifting Network (DS-Net), which serves as an effective panoptic segmentation framework in the point cloud realm and presents an efficient learnable clustering module, dynamic shifting, which adapts kernel functions on-the-fly for different instances.
66
LiDAR-based Panoptic Segmentation via Dynamic Shifting Network
Fangzhou Hong,Hui Zhou,Xinge Zhu,Hongsheng Li,Ziwei Liu +4 more
- 01 Jun 2021
TL;DR: DS-Net as mentioned in this paper adopts the cylinder convolution that is specifically designed for LiDAR point clouds, which serves as an effective panoptic segmentation framework in the point cloud realm.
References
•Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
- 01 Jan 2015
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
138.5K
ImageNet classification with deep convolutional neural networks
TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
•Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky,Ilya Sutskever,Geoffrey E. Hinton +2 more
- 03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TL;DR: This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
- 01 Jan 1998
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
53.5K