Hierarchical Surface Prediction for 3D Object Reconstruction
This addresses a major limitation in 3D geometry prediction for applications like computer vision and robotics, though it is an incremental improvement over existing CNN-based approaches.
The paper tackles the problem of coarse resolution in 3D object reconstruction from limited input data by proposing a hierarchical surface prediction framework that predicts high-resolution voxels only around surfaces, resulting in more accurate geometry predictions than low-resolution methods.
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.