A Combined Approach Toward Consistent Reconstructions of Indoor Spaces Based on 6D RGB-D Odometry and KinectFusion
This work addresses the need for accurate and efficient 3D reconstruction of indoor environments for applications like virtual worlds, though it is incremental as it builds on existing techniques.
The paper tackles the problem of reconstructing indoor spaces by combining 6D RGB-D odometry with KinectFusion, resulting in a method that outperforms state-of-the-art RGB-D SLAM systems in accuracy and outputs a ready-to-use polygon mesh without postprocessing.
We propose a 6D RGB-D odometry approach that finds the relative camera pose between consecutive RGB-D frames by keypoint extraction and feature matching both on the RGB and depth image planes. Furthermore, we feed the estimated pose to the highly accurate KinectFusion algorithm, which uses a fast ICP (Iterative Closest Point) to fine-tune the frame-to-frame relative pose and fuse the depth data into a global implicit surface. We evaluate our method on a publicly available RGB-D SLAM benchmark dataset by Sturm et al. The experimental results show that our proposed reconstruction method solely based on visual odometry and KinectFusion outperforms the state-of-the-art RGB-D SLAM system accuracy. Moreover, our algorithm outputs a ready-to-use polygon mesh (highly suitable for creating 3D virtual worlds) without any postprocessing steps.