A self-supervised feature adapter on DINOv2 enables zero-shot 9-DoF alignment of inexact CAD models to single images, validated on a new 20-category benchmark.
Learning 6d object pose estimation using 3d object coordinates
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
-
Zero-shot Inexact CAD Model Alignment from a Single Image
A self-supervised feature adapter on DINOv2 enables zero-shot 9-DoF alignment of inexact CAD models to single images, validated on a new 20-category benchmark.