.png){kind=icon}
.png){kind=icon}
Return
NeuPPS: Neural Piecewise Parametric Surfaces
.png){kind=icon}
PRE
AI
L
Y
C
G
C
A
S
J
W
DOI：10.1145/3771546.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Piecewise parametric surfaces have long been established as prevalent geometric representations; however, they often require surface refinement or sophisticated quadrangulation to accurately represent complex geometries. Geometric deep learning has shown that neural networks can provide greater representational power than conventional methods. Nevertheless, approaches using a single parametric surface for shape fitting struggle to capture fine-grained geometric details, while multi-patch methods fail to ensure seamless connections between adjacent patches. We present Neural Piecewise Parametric Surfaces (NeuPPS), the first piece-wise neural surface representation that allows for coarse patch layouts composed of arbitrary n-sided surface patches to model complex surface geometries with high precision, offering enhanced flexibility compared with traditional parametric surfaces. This new surface representation guarantees, by construction, the continuity between adjacent patches, a property that other neural patch-based approaches cannot ensure. Two novel components are introduced: a learnable feature complex and a continuous mapping function approximated by multi-layer perceptrons (MLPs). We apply the proposed NeuPPS to surface fitting and shape space learning tasks. Extensive experiments demonstrate the advantages of NeuPPS over traditional parametric representations and existing patch-based learning approaches.
Keywords:
Deep learning
Surface reconstruction
Journal
IF:
9.5
Papers:
4.7K
Citations:
3.6W
Organization
Cited Papers