CrossSDF learns a 3D signed distance field from planar cross-sections using a symmetric difference loss, adaptive sampling, and hybrid encoding, improving reconstruction of thin structures.
Sal: Sign agnostic learn- ing of shapes from raw data
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
CrossSDF: 3D Reconstruction of Thin Structures From Cross-Sections
CrossSDF learns a 3D signed distance field from planar cross-sections using a symmetric difference loss, adaptive sampling, and hybrid encoding, improving reconstruction of thin structures.