V-MIND lifts 2D instance masks to pseudo 3D boxes with monocular depth and camera intrinsics, then trains an indoor 3D detector with self-calibration and ambiguity losses, improving Omni3D indoor detection and enabling detection of new classes.
Coda: Col- laborative novel box discovery and cross-modal alignment for open-vocabulary 3d object detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
V-MIND: Building Versatile Monocular Indoor 3D Detector with Diverse 2D Annotations
V-MIND lifts 2D instance masks to pseudo 3D boxes with monocular depth and camera intrinsics, then trains an indoor 3D detector with self-calibration and ambiguity losses, improving Omni3D indoor detection and enabling detection of new classes.