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
Towards Open Vocabulary Learning: A Survey
Jianzong Wu,Xiangtai Li,Haobo Yuan,Henghui Ding,Yibo Yang,Xia Li,Jiangning Zhang,Yu Tong,Xudong Jiang,Bernard Ghanem,Dacheng Tao +10 more
TL;DR: Open Vocabulary Learning as discussed by the authors proposes to locate and recognize categories beyond the annotated label space, which is more general, practical, and effective compared to weakly supervised and zero-shot settings.
Infinite Variational Autoencoder for Semi-Supervised Learning
Ehsan Abbasnejad,Anthony Dick,Anton van den Hengel +2 more
- 01 Jul 2017
TL;DR: In this article, an infinite variational autoencoder (VAE) whose capacity adapts to suit the input data is presented using a mixture model where the mixing coefficients are modeled by a Dirichlet process, allowing them to integrate over the coefficients when performing inference.
66
Deep learning for the identification of bruised apples by fusing 3D deep features for apple grading systems
TL;DR: This paper investigated convolutional neural network-based predictive models for the identification of bruised apples based on shape information acquired from a 3D infrared imaging system and adopted transformation approaches so that geometric information located on 3D surface meshes could be efficiently converted to two-dimensional “image-like” feature maps.
66
NNWarp: Neural Network-Based Nonlinear Deformation
TL;DR: NNWarp as discussed by the authors reconstructs the force-displacement relation via warping the nodal displacement simulated using a simplistic constitutive model, which can handle a wide range of 3D models of various geometry.
66
From Point Clouds to Mesh Using Regression
Lubor Ladicky,Olivier Saurer,SoHyeon Jeong,Fabio Maninchedda,Marc Pollefeys +4 more
- 01 Oct 2017
TL;DR: This work designed a suitable feature vector and efficient oct-tree based GPU evaluation, capable of predicting surface of high resolution 3D models in milliseconds, and proposes to use a regression forest based method, which predicts the projection of a grid point to the surface, depending on the spatial configuration of point density in the grid point neighborhood.
66
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.