At the core of our framework is our novel self-evolved signed distance field (SeSDF) module which allows the framework to learn to deform the signed distance field (SDF) derived from the fitted SMPL-X model, such that detailed geometry reflecting the actual clothed human can be encoded for better reconstruction.

At the core of our framework is our novel self-evolved signed distance field (SeSDF) module which allows the framework to learn to deform the signed distance field (SDF) derived from the fitted SMPL-X model, such that detailed geometry reflecting the actual clothed human can be encoded for better reconstruction.

2023年4月1日 · At the core of our framework is our novel self-evolved signed distance field (SeSDF) module which allows the framework to learn to deform the signed distance field (SDF) derived from the fitted SMPL-X model, such that detailed geometry reflecting the actual clothed human can be encoded for better reconstruction.

In this paper, to extract more clothed human details flex-ibly and robustly from a single RGB image or uncalibrated multi-view RGB images, we present a novel framework, named SeSDF, that employs the parametric model SMPL-X [47] as a 3D prior and combines the merits of both im-plicit and explicit representations.

In this paper, to extract more clothed human details flexibly and robustly from a single RGB image or uncalibrated multi-view RGB images, we present a novel framework, named SeSDF, that employs the parametric model SMPL-X [47] as a 3D prior and combines the merits of both implicit and explicit representations.

At the core of our framework is our novel self-evolved signed distance field (SeSDF) module which allows the framework to learn to deform the signed distance field (SDF) derived from the fitted SMPL-X model, such that detailed geometry reflecting the actual clothed human can be encoded for better reconstruction.

2023年4月1日 · At the core of our framework is our novel self-evolved signed distance field (SeSDF) module which allows the framework to learn to deform the signed distance field (SDF)...

We address the problem of clothed human reconstruction from a single image or uncalibrated multiview images. existing methods struggle with reconstructing detailed geometry of a clothed human and often require a calibrated setting for multiview reconstruction. We propose a flexible framework which, by leveraging the parametric SMPL-X model, can take an arbitrary number of input images to ...

Our 3DFG-PIFu makes use of 3D Feature Grids to combine features from V images in a global manner (rather than point-wise or localized) and throughout the pipeline. Other than the 3D Feature Grids, 3DFG-PIFu also proposes an iterative mechanism that refines and updates an existing output human mesh using the different views.

图片格式为png、jpg，图片宽度*高度为300*38像素，不超过0.5mb