Preprint
Nov 2026
ELiCv2: Learned LiDAR Geometry Compression under Real-Time Embedded Constraints
Improving learned LiDAR compression increasingly relies on heavier inference, making it harder to meet the constraints of real-time embedded systems. We present ELiCv2, which removes two sources of redundant computation in progressive coding. Its discrete entropy interface selects a precomputed integer CDF instead of m...
Soowoong Kim, Junsik Kim, Bang Gun et al.
· 0 citations