Dynamicfusion: Reconstruction and tracking of non-rigid scenes in real-time

Figure 1: Real-time reconstructions of a moving scene with DynamicFusion; both the person and the camera are moving. The initially noisy and incomplete model is progressively denoised and completed over time (left to right). We present the first dense SLAM system capable of re-constructing non-rigidly deforming scenes in real-time, by fusing together RGBD scans captured from commodity sen-sors. Our DynamicFusion approach reconstructs scene ge-ometry whilst simultaneously estimating a dense volumet-ric 6D motion field that warps the estimated geometry into a live frame. Like KinectFusion, our system produces in-creasingly denoised, detailed, and complete reconstructions as more measurements are fused, and displays the updated model in real time. Because we do not require a template or other prior scene model, the approach is applicable to a wide range of moving objects and scenes