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
MeshCNN: A Network with an Edge
TL;DR: MeshCNN as discussed by the authors combines specialized convolution and pooling layers that operate on the mesh edges, by leveraging their intrinsic geodesic connections, and learns which edges to collapse, thus forming a task-driven process where the network exposes and expands the important features while discarding the redundant ones.
DeepIM: Deep Iterative Matching for 6D Pose Estimation
TL;DR: A novel deep neural network for 6D pose matching named DeepIM is proposed, trained to predict a relative pose transformation using a disentangled representation of 3D location and 3D orientation and an iterative training process.
575
•Proceedings Article
Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision
Xinchen Yan,Jimei Yang,Ersin Yumer,Yijie Guo,Honglak Lee +4 more
- 01 Jan 2016
TL;DR: An encoder-decoder network with a novel projection loss defined by the projective transformation enables the unsupervised learning using 2D observation without explicit 3D supervision and shows superior performance and better generalization ability for 3D object reconstruction when the projection loss is involved.
564
Multi-view 3D Models from Single Images with a Convolutional Network
Maxim Tatarchenko,Alexey Dosovitskiy,Thomas Brox +2 more
- 08 Oct 2016
TL;DR: In this paper, a convolutional network is trained on renderings of synthetic 3D models of cars and chairs to predict an RGB image and a depth map of the object as seen from an arbitrary view.
ABC: A Big CAD Model Dataset for Geometric Deep Learning
Sebastian Koch,Albert Matveev,Zhongshi Jiang,Francis Williams,Alexey Artemov,Evgeny Burnaev,Marc Alexa,Denis Zorin,Daniele Panozzo +8 more
- 01 Jun 2019
TL;DR: This work performs a large-scale benchmark for estimation of surface normals, comparing existing data driven methods and evaluating their performance against both the ground truth and traditional normal estimation methods.
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.