Computer Vision and Pattern Recognition (CVPR 2021)
NormalFusion: Real-Time Acquisition of Surface Normals for High-Resolution RGB-D Scanning
Hyunho Ha
Joo Ho Lee
Andreas Meuleman
Min H. Kim
KAIST
University of Tuebingen
Result of our real-time normal fusion method,
compared with the conventional fusion method that accumulates
TSDFs of depth maps in the canonical space. We
decompose camera signals to photometric normals and accumulate
them in texture space associated with voxel grids
of TSDFs, enabling high-resolution geometry in real-time.
Refer to the supplemental video for real-time demo.
CVPR 2021 presentation
Supplemental video
Abstract
Multiview shape-from-shading (SfS) has achieved high-detail geometry, but its computation is expensive for solving a multiview registration and an ill-posed inverse rendering problem. Therefore, it has been mainly used for offline methods. Volumetric fusion enables real-time scanning using a conventional RGB-D camera, but its geometry resolution has been limited by the grid resolution of the volumetric distance field and depth registration errors. In this paper, we propose a real-time scanning method that can acquire high-detail geometry by bridging volumetric fusion and multiview SfS in two steps. First, we propose the first real-time acquisition of photometric normals stored in texture space to achieve high-detail geometry. We also introduce geometry-aware texture mapping, which progressively refines geometric registration between the texture space and the volumetric distance field by means of normal texture, achieving real-time multiview SfS. We demonstrate our scanning of high-detail geometry using an RGB-D camera at ~20 fps. Results verify that the geometry quality of our method is strongly competitive with that of offline multi-view SfS methods.
BibTeX
@InProceedings{Ha_2021_CVPR,
author = {Hyunho Ha and Joo Ho Lee and Andreas Meuleman
and Min H. Kim},
title = {NormalFusion: Real-Time Acquisition of Surface
Normals for High-Resolution RGB-D Scanning},
booktitle = {IEEE Conference on Computer Vision and
Pattern Recognition (CVPR)},
month = {June},
year = {2021}
}
