Pixel2ISDF: Implicit Signed Distance Fields based Human Body Model from Multi-view and Multi-pose Images
In this report, we focus on reconstructing clothed humans in the canonical space given multiple views and poses of a human as the input. To achieve this, we utilize the geometric prior of the SMPLX model in the canonical space to learn the implicit representation for geometry reconstruction. Based o...
Gespeichert in:
Hauptverfasser: | , , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | In this report, we focus on reconstructing clothed humans in the canonical
space given multiple views and poses of a human as the input. To achieve this,
we utilize the geometric prior of the SMPLX model in the canonical space to
learn the implicit representation for geometry reconstruction. Based on the
observation that the topology between the posed mesh and the mesh in the
canonical space are consistent, we propose to learn latent codes on the posed
mesh by leveraging multiple input images and then assign the latent codes to
the mesh in the canonical space. Specifically, we first leverage normal and
geometry networks to extract the feature vector for each vertex on the SMPLX
mesh. Normal maps are adopted for better generalization to unseen images
compared to 2D images. Then, features for each vertex on the posed mesh from
multiple images are integrated by MLPs. The integrated features acting as the
latent code are anchored to the SMPLX mesh in the canonical space. Finally,
latent code for each 3D point is extracted and utilized to calculate the SDF.
Our work for reconstructing the human shape on canonical pose achieves 3rd
performance on WCPA MVP-Human Body Challenge. |
---|---|
DOI: | 10.48550/arxiv.2212.02765 |