Robust 3D Self-portraits in Seconds
This addresses the need for fast, accessible 3D avatar creation for applications like VR/AR, though it appears incremental in improving existing reconstruction pipelines.
The paper tackles the problem of creating detailed 3D self-portraits from a single RGBD camera, achieving reconstruction in seconds with robustness to loose clothing. It demonstrates improved efficiency and robustness compared to state-of-the-art methods.
In this paper, we propose an efficient method for robust 3D self-portraits using a single RGBD camera. Benefiting from the proposed PIFusion and lightweight bundle adjustment algorithm, our method can generate detailed 3D self-portraits in seconds and shows the ability to handle subjects wearing extremely loose clothes. To achieve highly efficient and robust reconstruction, we propose PIFusion, which combines learning-based 3D recovery with volumetric non-rigid fusion to generate accurate sparse partial scans of the subject. Moreover, a non-rigid volumetric deformation method is proposed to continuously refine the learned shape prior. Finally, a lightweight bundle adjustment algorithm is proposed to guarantee that all the partial scans can not only "loop" with each other but also remain consistent with the selected live key observations. The results and experiments show that the proposed method achieves more robust and efficient 3D self-portraits compared with state-of-the-art methods.