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.
Esc-net: Alleviating triple sparsity on 3d lidar point clouds for extreme sparse scene 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.