The paper introduces ADIW, a 564K-image pseudo-labeled dataset for relative amodal depth, and two fine-tuned models (Amodal-DAV2 and Amodal-DepthFM) that predict occluded-object depth from an image, observed depth, and amodal mask.
Adabins: Depth estimation using adaptive bins
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Amodal Depth Anything: Amodal Depth Estimation in the Wild
The paper introduces ADIW, a 564K-image pseudo-labeled dataset for relative amodal depth, and two fine-tuned models (Amodal-DAV2 and Amodal-DepthFM) that predict occluded-object depth from an image, observed depth, and amodal mask.