Pixel2ISDF: Implicit Signed Distance Fields based Human Body Model from Multi-view and Multi-pose Images

12/06/2022
by   Jianchuan Chen, et al.
0

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.

READ FULL TEXT
research
06/29/2023

Representation learning of vertex heatmaps for 3D human mesh reconstruction from multi-view images

This study addresses the problem of 3D human mesh reconstruction from mu...
research
10/04/2022

Multi-view Human Body Mesh Translator

Existing methods for human mesh recovery mainly focus on single-view fra...
research
12/31/2020

Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans

This paper addresses the challenge of novel view synthesis for a human p...
research
05/23/2020

Unsupervised Geometric Disentanglement for Surfaces via CFAN-VAE

For non-Euclidean data such as meshes of humans, a prominent task for ge...
research
01/05/2022

Surface-Aligned Neural Radiance Fields for Controllable 3D Human Synthesis

We propose a new method for reconstructing controllable implicit 3D huma...
research
08/05/2019

Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation

We study the problem of shape generation in 3D mesh representation from ...
research
07/03/2023

VINECS: Video-based Neural Character Skinning

Rigging and skinning clothed human avatars is a challenging task and tra...

Please sign up or login with your details

Forgot password? Click here to reset