Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs
Maxim Tatarchenko,Alexey Dosovitskiy,Thomas Brox +2 more
- pp 2107-2115
Reads0
Chats0
TLDR
In this paper, a deep convolutional decoder architecture is proposed to generate volumetric 3D outputs in a compute-and memory-efficient manner by using an octree representation.Abstract:
We present a deep convolutional decoder architecture that can generate volumetric 3D outputs in a compute- and memory-efficient manner by using an octree representation. The network learns to predict both the structure of the octree, and the occupancy values of individual cells. This makes it a particularly valuable technique for generating 3D shapes. In contrast to standard decoders acting on regular voxel grids, the architecture does not have cubic complexity. This allows representing much higher resolution outputs with a limited memory budget. We demonstrate this in several application domains, including 3D convolutional autoencoders, generation of objects and whole scenes from high-level representations, and shape from a single image.read more
Citations
More filters
Journal ArticleDOI
Dynamic Graph CNN for Learning on Point Clouds
TL;DR: This work proposes a new neural network module suitable for CNN-based high-level tasks on point clouds, including classification and segmentation called EdgeConv, which acts on graphs dynamically computed in each layer of the network.
Proceedings ArticleDOI
DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation
TL;DR: DeepSDF as mentioned in this paper represents a shape's surface by a continuous volumetric field: the magnitude of a point in the field represents the distance to the surface boundary and the sign indicates whether the region is inside (-) or outside (+) of the shape.
Proceedings ArticleDOI
Learning Implicit Fields for Generative Shape Modeling
Zhiqin Chen,Hao Zhang +1 more
TL;DR: In this paper, an implicit field is used to assign a value to each point in 3D space, so that a shape can be extracted as an iso-surface, and a binary classifier is trained to perform this assignment.
Posted Content
Occupancy Networks: Learning 3D Reconstruction in Function Space
TL;DR: This paper proposes Occupancy Networks, a new representation for learning-based 3D reconstruction methods that encodes a description of the 3D output at infinite resolution without excessive memory footprint, and validate that the representation can efficiently encode 3D structure and can be inferred from various kinds of input.
Proceedings ArticleDOI
Occupancy Networks: Learning 3D Reconstruction in Function Space
TL;DR: In this paper, the authors propose Occupancy Networks, which implicitly represent the 3D surface as the continuous decision boundary of a deep neural network classifier, which can be used for learning-based 3D reconstruction methods.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
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.
Proceedings ArticleDOI
Caffe: Convolutional Architecture for Fast Feature Embedding
Yangqing Jia,Evan Shelhamer,Jeff Donahue,Sergey Karayev,Jonathan Long,Ross Girshick,Sergio Guadarrama,Trevor Darrell +7 more
TL;DR: Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures.
Proceedings ArticleDOI
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
TL;DR: This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.
Book ChapterDOI
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
TL;DR: In this paper, the authors combine the benefits of both approaches, and propose the use of perceptual loss functions for training feed-forward networks for image style transfer, where a feedforward network is trained to solve the optimization problem proposed by Gatys et al. in real-time.
Book ChapterDOI
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
Özgün Çiçek,Ahmed Abdulkadir,Ahmed Abdulkadir,Soeren S. Lienkamp,Thomas Brox,Olaf Ronneberger,Olaf Ronneberger +6 more
TL;DR: In this paper, the authors propose a network for volumetric segmentation that learns from sparsely annotated volumetrized images, which is trained end-to-end from scratch, i.e., no pre-trained network is required.