no code implementations • CVPR 2023 • Dae-Young Song, HeeKyung Lee, Jeongil Seo, Donghyeon Cho
Beyond the SMPL, which provides skinned parametric human 3D information, in this paper, we propose a new IF-based method, DIFu, that utilizes a projected depth prior containing textured and non-parametric human 3D information.
no code implementations • 13 Sep 2022 • Dae-Young Song, Geonsoo Lee, HeeKyung Lee, Gi-Mun Um, Donghyeon Cho
Recently, there has been growing attention on an end-to-end deep learning-based stitching model.