Predicting the Next Best View for 3D Mesh Refinement

TL;DR

This paper introduces a mesh-based method for predicting the next best view in 3D reconstruction, focusing on the worst reconstructed regions to improve accuracy efficiently.

Contribution

It proposes a novel mesh-focused approach with a photo-consistent index and energy function that outperforms voxel-based methods in 3D scene reconstruction.

Findings

Achieves state-of-the-art results on a standard dataset.

Efficiently targets worst reconstructed regions for view planning.

Reduces memory requirements compared to voxel-based methods.

Abstract

3D reconstruction is a core task in many applications such as robot navigation or sites inspections. Finding the best poses to capture part of the scene is one of the most challenging topic that goes under the name of Next Best View. Recently, many volumetric methods have been proposed; they choose the Next Best View by reasoning over a 3D voxelized space and by finding which pose minimizes the uncertainty decoded into the voxels. Such methods are effective, but they do not scale well since the underlaying representation requires a huge amount of memory. In this paper we propose a novel mesh-based approach which focuses on the worst reconstructed region of the environment mesh. We define a photo-consistent index to evaluate the 3D mesh accuracy, and an energy function over the worst regions of the mesh which takes into account the mutual parallax with respect to the previous cameras, the angle of incidence of the viewing ray to the surface and the visibility of the region. We test our approach over a well known dataset and achieve state-of-the-art results.