A method that optimizes 3D Bezier curves to abstract a 3D shape, capturing geometry and texture through CLIP-guided losses, with keypoint-based user control and SDF-based deformation handles.
Spatial correlation and value prediction in convolutional neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
WIR3D: Visually-Informed and Geometry-Aware 3D Shape Abstraction
A method that optimizes 3D Bezier curves to abstract a 3D shape, capturing geometry and texture through CLIP-guided losses, with keypoint-based user control and SDF-based deformation handles.