SerLiC compresses LiDAR reflectance losslessly by serializing points along the sensor's scan order and using a Mamba sequence model to predict each value, beating prior codecs by up to 22% in bitrate with 98% fewer parameters.
Title resolution pending
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
-
Efficient LiDAR Reflectance Compression via Scanning Serialization
SerLiC compresses LiDAR reflectance losslessly by serializing points along the sensor's scan order and using a Mamba sequence model to predict each value, beating prior codecs by up to 22% in bitrate with 98% fewer parameters.