Efficient Online Surface Correction for Real-time Large-Scale 3D Reconstruction
This work addresses real-time, globally consistent dense 3D reconstruction for applications like robotics or augmented reality, representing an incremental improvement over existing methods.
The paper tackles the problem of drift in camera tracking for large-scale 3D reconstruction by proposing an efficient on-the-fly surface correction method that updates the reconstructed surface during pose changes, achieving up to 93% more runtime efficiency and significantly less memory usage with negligible loss of surface quality.
State-of-the-art methods for large-scale 3D reconstruction from RGB-D sensors usually reduce drift in camera tracking by globally optimizing the estimated camera poses in real-time without simultaneously updating the reconstructed surface on pose changes. We propose an efficient on-the-fly surface correction method for globally consistent dense 3D reconstruction of large-scale scenes. Our approach uses a dense Visual RGB-D SLAM system that estimates the camera motion in real-time on a CPU and refines it in a global pose graph optimization. Consecutive RGB-D frames are locally fused into keyframes, which are incorporated into a sparse voxel hashed Signed Distance Field (SDF) on the GPU. On pose graph updates, the SDF volume is corrected on-the-fly using a novel keyframe re-integration strategy with reduced GPU-host streaming. We demonstrate in an extensive quantitative evaluation that our method is up to 93% more runtime efficient compared to the state-of-the-art and requires significantly less memory, with only negligible loss of surface quality. Overall, our system requires only a single GPU and allows for real-time surface correction of large environments.