PLOT generates 3D bounding-box labels for objects from monocular video alone, using point tracking, estimated camera motion, and temporal fusion of pseudo-LiDAR, without auxiliary sensors or model training.
In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
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
-
PLOT: Pseudo-Labeling via Object Tracking for Monocular 3D Object Detection
PLOT generates 3D bounding-box labels for objects from monocular video alone, using point tracking, estimated camera motion, and temporal fusion of pseudo-LiDAR, without auxiliary sensors or model training.