A new corrupted point cloud completion benchmark and a network with contrastive feature filtering report top scores after fine-tuning, yet exhibit unexplained catastrophic failures on two corruptions.
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
-
Denoising-While-Completing Network (DWCNet): Robust Point Cloud Completion Under Corruption
A new corrupted point cloud completion benchmark and a network with contrastive feature filtering report top scores after fine-tuning, yet exhibit unexplained catastrophic failures on two corruptions.