A single-view 3D reconstruction network that refines a category-averaged prior shape achieves few-shot generalization to novel object classes without retraining or novel-class images.
Learning priors for se- mantic 3d reconstruction
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
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Few-Shot Generalization for Single-Image 3D Reconstruction via Priors
A single-view 3D reconstruction network that refines a category-averaged prior shape achieves few-shot generalization to novel object classes without retraining or novel-class images.