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
Attentional ShapeContextNet for Point Cloud Recognition
Saining Xie,Sainan Liu,Zeyu Chen,Zhuowen Tu +3 more
- 18 Jun 2018
TL;DR: The resulting model, called ShapeContextNet, consists of a hierarchy with modules not relying on a fixed grid while still enjoying properties similar to those in convolutional neural networks - being able to capture and propagate the object part information.
The Perfect Match: 3D Point Cloud Matching With Smoothed Densities
Zan Gojcic,Caifa Zhou,Jan Dirk Wegner,Andreas Wieser +3 more
- 15 Jun 2019
TL;DR: 3DSmoothNet as mentioned in this paper uses a voxelized smoothed density value (SDV) representation to match 3D point clouds with a siamese deep learning architecture and fully convolutional layers.
•Posted Content
Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction
TL;DR: This paper uses 2D convolutional operations to predict the 3D structure from multiple viewpoints and jointly apply geometric reasoning with 2D projection optimization, and introduces the pseudo-renderer, a differentiable module to approximate the true rendering operation, to synthesize novel depth maps for optimization.
3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans
Ji Hou,Angela Dai,Matthias NieBner +2 more
- 15 Jun 2019
TL;DR: 3D-SIS is introduced, a novel neural network architecture for 3D semantic instance segmentation in commodity RGB-D scans that leverages high-resolution RGB input by associating 2D images with the volumetric grid based on the pose alignment of the 3D reconstruction.
Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review
TL;DR: A review of recent deep-learning-based data fusion approaches that leverage both image and point cloud data processing and identifies gaps and over-looked challenges between current academic researches and real-world applications.
470
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.