A fine-to-coarse training scheme for cuboid shape abstraction achieves more accurate and more compact 3D shape representations than prior cuboid-based methods.
ACM Transactions on Graphics (TOG) 38, 6 (2019)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Fine-to-Coarse Cuboid Shape Abstraction
A fine-to-coarse training scheme for cuboid shape abstraction achieves more accurate and more compact 3D shape representations than prior cuboid-based methods.