3D ShapeNets: A deep representation for volumetric shapes
Zhirong Wu,Shuran Song,Aditya Khosla,Fisher Yu,Linguang Zhang,Xiaoou Tang,Jianxiong Xiao +6 more
- 07 Jun 2015
- pp 1912-1920
TL;DR: This work proposes to represent a geometric 3D shape as a probability distribution of binary variables on a 3D voxel grid, using a Convolutional Deep Belief Network, and shows that this 3D deep representation enables significant performance improvement over the-state-of-the-arts in a variety of tasks.
read more
Abstract: 3D shape is a crucial but heavily underutilized cue in today's computer vision systems, mostly due to the lack of a good generic shape representation. With the recent availability of inexpensive 2.5D depth sensors (e.g. Microsoft Kinect), it is becoming increasingly important to have a powerful 3D shape representation in the loop. Apart from category recognition, recovering full 3D shapes from view-based 2.5D depth maps is also a critical part of visual understanding. To this end, we propose to represent a geometric 3D shape as a probability distribution of binary variables on a 3D voxel grid, using a Convolutional Deep Belief Network. Our model, 3D ShapeNets, learns the distribution of complex 3D shapes across different object categories and arbitrary poses from raw CAD data, and discovers hierarchical compositional part representation automatically. It naturally supports joint object recognition and shape completion from 2.5D depth maps, and it enables active object recognition through view planning. To train our 3D deep learning model, we construct ModelNet - a large-scale 3D CAD model dataset. Extensive experiments show that our 3D deep representation enables significant performance improvement over the-state-of-the-arts in a variety of tasks.
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
•Posted Content
Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling
TL;DR: PointNet as discussed by the authors proposes a point-set kernel as a set of learnable 3D points that jointly respond to neighboring data points according to their geometric affinities measured by kernel correlation, adapted from a similar technique for point cloud registration.
309
ConvPoint: Continuous convolutions for point cloud processing
TL;DR: A generalization of discrete convolutional neural networks in order to deal with point clouds by replacing discrete kernels by continuous ones is proposed, which is simple, allows arbitrary point cloud sizes and can easily be used for designing neural networks similarly to 2D CNNs.
308
Escaping Plato’s Cave: 3D Shape From Adversarial Rendering
Philipp Henzler,Niloy J. Mitra,Tobias Ritschel +2 more
- 01 Oct 2019
TL;DR: PlatonicGAN as discussed by the authors uses a deep neural network to generate 3D shapes which, when rendered to images, are indistinguishable from ground truth images (for a discriminator) under various camera poses.
HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-Scale Point Clouds
Xiuye Gu,Yijie Wang,Chongruo Wu,Yong Jae Lee,Panqu Wang +4 more
- 15 Jun 2019
TL;DR: A novel deep neural network architecture for end-to-end scene flow estimation that directly operates on large-scale 3D point clouds is presented and shows great generalization ability on real-world data and on different point densities without fine-tuning.
(AF) 2 -S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network
Ran Cheng,Ryan Razani,Ehsan Taghavi,Enxu Li,Bingbing Liu +4 more
- 20 Jun 2021
TL;DR: In this paper, an end-to-end encoder-decoder CNN network for 3D LiDAR semantic segmentation is proposed, where a multibranch attentive feature fusion module in the encoder and a unique adaptive feature selection module with feature map re-weighting in the decoder are introduced.
303
References
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.
A method for registration of 3-D shapes
Paul J. Besl,H.D. McKay +1 more
TL;DR: In this paper, the authors describe a general-purpose representation-independent method for the accurate and computationally efficient registration of 3D shapes including free-form curves and surfaces, based on the iterative closest point (ICP) algorithm, which requires only a procedure to find the closest point on a geometric entity to a given point.
20.6K
A fast learning algorithm for deep belief nets
TL;DR: A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory.
Object Detection with Discriminatively Trained Part-Based Models
TL;DR: An object detection system based on mixtures of multiscale deformable part models that is able to represent highly variable object classes and achieves state-of-the-art results in the PASCAL object detection challenges is described.