RefComp completes partial 3D point clouds by fusing features of retrieved reference shapes into the input's latent representation, and it can be trained jointly across object classes.
Sparse fuse dense: Towards high quality 3d detection with depth completion,
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
-
RefComp: A Reference-guided Unified Framework for Unpaired Point Cloud Completion
RefComp completes partial 3D point clouds by fusing features of retrieved reference shapes into the input's latent representation, and it can be trained jointly across object classes.