Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations

TL;DR

This paper introduces a novel adaptive octree-based graph neural network for efficient and high-quality 3D shape reconstruction and auto-encoding, leveraging a new graph convolution operator over dual octree graphs.

Contribution

It proposes a dual octree graph network with a new graph convolution operator for efficient 3D shape representation and reconstruction, improving performance and reducing computational costs.

Findings

Outperforms existing methods in 3D shape reconstruction tasks.

Effectively encodes detailed shape features.

Demonstrates good generality across different shape categories.

Abstract

We present an adaptive deep representation of volumetric fields of 3D shapes and an efficient approach to learn this deep representation for high-quality 3D shape reconstruction and auto-encoding. Our method encodes the volumetric field of a 3D shape with an adaptive feature volume organized by an octree and applies a compact multilayer perceptron network for mapping the features to the field value at each 3D position. An encoder-decoder network is designed to learn the adaptive feature volume based on the graph convolutions over the dual graph of octree nodes. The core of our network is a new graph convolution operator defined over a regular grid of features fused from irregular neighboring octree nodes at different levels, which not only reduces the computational and memory cost of the convolutions over irregular neighboring octree nodes, but also improves the performance of feature learning. Our method effectively encodes shape details, enables fast 3D shape reconstruction, and exhibits good generality for modeling 3D shapes out of training categories. We evaluate our method on a set of reconstruction tasks of 3D shapes and scenes and validate its superiority over other existing approaches. Our code, data, and trained models are available at https://wang-ps.github.io/dualocnn.