Neural Vector Fields for Surface Representation and Inference

04/13/2022
by   Edoardo Mello Rella, et al.
0

Neural implicit fields have recently been shown to represent 3D shapes accurately, opening up various applications in 3D shape analysis. Up to now, such implicit fields for 3D representation are scalar, encoding the signed distance or binary volume occupancy and more recently the unsigned distance. However, the first two can only represent closed shapes, while the unsigned distance has difficulties in accurate and fast shape inference. In this paper, we propose a Neural Vector Field for shape representation in order to overcome the two aforementioned problems. Mapping each point in space to the direction towards the closest surface, we can represent any type of shape. Similarly the shape mesh can be reconstructed by applying the marching cubes algorithm, with proposed small changes, on top of the inferred vector field. We compare the method on ShapeNet where the proposed new neural implicit field shows superior accuracy in representing both closed and open shapes outperforming previous methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/06/2018

Learning Implicit Fields for Generative Shape Modeling

We advocate the use of implicit fields for learning generative models of...
research
07/23/2021

A Deep Signed Directional Distance Function for Object Shape Representation

Neural networks that map 3D coordinates to signed distance function (SDF...
research
06/07/2021

Deep Medial Fields

Implicit representations of geometry, such as occupancy fields or signed...
research
09/04/2023

Neural Vector Fields: Generalizing Distance Vector Fields by Codebooks and Zero-Curl Regularization

Recent neural networks based surface reconstruction can be roughly divid...
research
03/08/2023

Neural Vector Fields: Implicit Representation by Explicit Learning

Deep neural networks (DNNs) are widely applied for nowadays 3D surface r...
research
07/18/2022

Latent Partition Implicit with Surface Codes for 3D Representation

Deep implicit functions have shown remarkable shape modeling ability in ...
research
03/29/2023

CN-DHF: Compact Neural Double Height-Field Representations of 3D Shapes

We introduce CN-DHF (Compact Neural Double-Height-Field), a novel hybrid...

Please sign up or login with your details

Forgot password? Click here to reset