REALISTIC SURFACE GEOMETRY RECONSTRUCTION
USING A HANDHELD RGB-D CAMERA

Kyoung-Rok Lee, Truong Q. Nguyen

Video Processing Lab

University of California, San Diego

 

Abstract

In this paper, we have proposed a novel approach for the reconstruction of real object/scene with realistic surface geometry using handheld, low-cost, depth and color cameras. To achieve accurate reconstruction, the most important issues to consider are the quality of the geometry information provided and the global alignment method between frames. In our approach, new surface geometry refinement is used to recover finer-scale surface geometry from depth data by utilizing high quality RGB images. In addition, a weighted multi-scale iterative closest point (ICP) method is exploited to align each scan to the global model accurately. We show the effectiveness of the proposed surface geometry refinement method by comparing it with other depth refinement methods. We also show both the qualitative and quantitative results of reconstructed models by comparing it with other reconstruction methods.

Experiments

1. Qualitative Results: Click picture to download the corresponding mesh model file (.ply)

  Anatomy Apollo Lion
Color Image
Laser Scan
SCENECT
KinectFusion
Proposed Method

 

2. Quantitative Results

Accuracy: The accuracy represents the distance (error) in which a given percentage of the reconstruction is within the distance from the ground truth model

Anatomy Apollo Lion

 

3.Human Bust Reconstruction

;
;
;
;