FILTR predicts persistence diagrams from pretrained 3D encoders on the new DONUT benchmark, showing limited topological signals in encoders but successful approximation via learnable feed-forward.
latent prediction pretraining In this work, we focus on encoders pretrained with a 3D re- construction objective
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FILTR: Extracting Topological Features from Pretrained 3D Models
FILTR predicts persistence diagrams from pretrained 3D encoders on the new DONUT benchmark, showing limited topological signals in encoders but successful approximation via learnable feed-forward.