ICON: Implicit Clothed humans Obtained from Normals

IntrinsicNGP: Intrinsic Coordinate based Hash Encoding for Human NeRF

“…PHORHUM [3] modifies the geometric representation to SDF to get finer geometry and normal, so they can simultaneously estimate detailed 3D geometry and the unshaded surface color together with the scene illumination. ICON [33] infers a 3D clothed human meshes from a color image by utilizing a body-guided normal prediction model and a local-feature-based implicit 3D representation conditioned on SMPL(-X). SelfRecon [10] represents the human body as a template mesh and SDF in canonical space and utilizes a deformation field consisting of rigid forward LBS deformation and small non-rigid deformation to generate correspondences.…”

gDNA: Towards Generative Detailed Neural Avatars

“…To overcome the topology and resolution limitations of meshes, other representations, including point clouds [35,37,65], implicit surfaces [12,47,52,55,58,60], and radiance fields [32,45,49,56,63], have been explored. In particular, neural implicit surface representations have emerged as a powerful tool to model 3D (clothed) human shapes [6,15,17,20,21,30,41,50,51,62,66,67] due to their topological flexibility and resolution independence. Recent work [12,52,58] uses implicit surfaces to learn human avatars for a single subject, wearing a specific garment.…”

PINA: Learning a Personalized Implicit Neural Avatar from a Single RGB-D Video Sequence

“…Implicit Human Models from 3D Scans Implicit neural representations [14,37,43] can handle topological changes better [10,44] and have been used to reconstruct clothed human shapes [12,26,27,30,48,49,51,52,59]. Typically, based on a learned prior from large-scale datasets, they recover the geometry of clothed humans from images [51,52,59,66] or point clouds [15]. However, these reconstructions are static and cannot be reposed.…”