Hierarchical Surface Prediction for 3D Object Reconstruction

TL;DR

This paper introduces a hierarchical surface prediction framework that enables high-resolution 3D object surface reconstruction from various input types, improving accuracy over traditional coarse voxel predictions.

Contribution

The paper presents a novel hierarchical surface prediction method that predicts high-resolution surface voxels efficiently, enhancing 3D reconstruction quality from limited input data.

Findings

High-resolution surface predictions are more accurate than low-resolution ones.

The method works effectively with color images, depth images, and partial voxel grids.

The approach is not dependent on specific input types.

Abstract

Recently, Convolutional Neural Networks have shown promising results for 3D geometry prediction. They can make predictions from very little input data such as a single color image. A major limitation of such approaches is that they only predict a coarse resolution voxel grid, which does not capture the surface of the objects well. We propose a general framework, called hierarchical surface prediction (HSP), which facilitates prediction of high resolution voxel grids. The main insight is that it is sufficient to predict high resolution voxels around the predicted surfaces. The exterior and interior of the objects can be represented with coarse resolution voxels. Our approach is not dependent on a specific input type. We show results for geometry prediction from color images, depth images and shape completion from partial voxel grids. Our analysis shows that our high resolution predictions are more accurate than low resolution predictions.