A retrieval-augmented cross-modal framework with structural shared encoding and gated reference priors is claimed to achieve state-of-the-art point cloud completion, although the evaluation may be tainted by same-object retrieval leakage.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Benefit from Reference: Retrieval-Augmented Cross-modal Point Cloud Completion
A retrieval-augmented cross-modal framework with structural shared encoding and gated reference priors is claimed to achieve state-of-the-art point cloud completion, although the evaluation may be tainted by same-object retrieval leakage.