SAM4D is a promptable model that segments and tracks objects across camera and LiDAR streams with cross-modal prompts, trained on pseudo-labels generated by an automated data engine.
Better call sal: Towards learning to segment anything in lidar
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
-
SAM4D: Segment Anything in Camera and LiDAR Streams
SAM4D is a promptable model that segments and tracks objects across camera and LiDAR streams with cross-modal prompts, trained on pseudo-labels generated by an automated data engine.