Mar 14, 2023 · Abstract:We study the problem of reconstructing 3D feature curves of an object from a set of calibrated multi-view images.

Inspired by NeRF, NEF is optimized with a view-based rendering loss where a 2D edge map is rendered at a given view and is compared to the ground-truth edge map ...

To obtain 3D parametric curves from multi-view images, the method consists of two steps: building neural edge fields. (NEF) and reconstructing parametric curves ...

This work learns a neural implicit field representing the density distribution of 3D edges which is implemented as Neural Edge Field (NEF), ...

We study the problem of reconstructing 3D feature curves of an object from a set of calibrated multi-view images. To do so, we learn a neural implicit field ...

To obtain 3D parametric curves from multi-view images, the method consists of two steps: building neural edge fields (NEF) and reconstructing parametric curves.

NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction from Multi-view Images ... This is the repository that contains source code for the NEF website. If ...

Researchers developed a method called Neural Edge Field (NEF) to reconstruct 3D feature curves from 2D images. They trained NEF to detect edges and then ...

We study the problem of reconstructing 3D feature curves of an object from a set of calibrated multi-view images. To do so, we learn a neural implicit field ...