Dec 5, 2017 · We present O-CNN, an Octree-based Convolutional Neural Network (CNN) for 3D shape analysis. Built upon the octree representation of 3D shapes.
We present O-CNN, an Octree-based Convolutional Neural Network (CNN) for 3D shape analysis. Built upon the octree representation of 3D shapes.
microsoft/O-CNN: O-CNN: Octree-based Convolutional Neural ... - GitHub
github.com › microsoft › O-CNN
This repository contains the implementation of our papers related with O-CNN. The code is released under the MIT license.
Aug 6, 2025 · We present O-CNN, an Octree-based Convolutional Neural Network (CNN) for 3D shape analysis. Built upon the octree representation of 3D shapes, ...
We present O-CNN, an Octree-based Convolutional Neural Network (CNN) for 3D shape analysis. Built upon the octree representation of 3D shapes, our method ...
O-CNN is an octree-based 3D convolutional neural network framework for 3D data. O-CNN constrains the CNN storage and computation into non-empty sparse voxels ...
O-CNN supports various CNN structures and works for 3D shapes in different representations. By restraining the computations on the octants occupied by 3D ...
We present an Adaptive Octree-based Convolutional Neural Network (Adaptive O-CNN) for efficient 3D shape encoding and decoding.
We present O-CNN, an Octree-based Convolutional Neural Network (CNN) 1 INTRODUCTION. for 3D shape analysis. Built upon the octree representation of 3D shapes, ...
We show that with these simple adaptions — output-guided skip-connection and deeper O-CNN (up to 70 layers), our network achieves state-of-the-art results in 3D.