With the majority of research, in relation to 3D object reconstruction, focusing on single static synthetic object reconstruction, there is a need for a method capable of reconstructing morphing objects in dynamic scenes without external influence. However, such research requires a time-consuming creation of real world object ground truths. To solve this, we propose a novel three-staged deep adversarial neural network architecture capable of denoising and refining real-world depth sensor input for full human body posture reconstruction. The proposed network has achieved Earth Mover and Chamfer distances of 0.059 and 0.079 on synthetic datasets, respectively, which indicates on-par experimental results with other approaches, in addition to the ability of reconstructing from maskless real world depth frames. Additional visual inspection to the reconstructed pointclouds has shown that the suggested approach manages to deal with the majority of the real world depth sensor noise, with the exception of large deformities to the depth field.
Keywords: adversarial auto-refinement; human shape reconstruction; pointcloud reconstruction.