AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

ELiC: Efficient LiDAR Geometry Compression via Cross-Bit-depth Feature Propagation and Bag-of-Encoders

Junsik Kim, Gun Bang, Soowoong Kim

CVPR 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Joint pruning and quantization · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add cross-bit-depth feature propagation (ablation)RENO-style coding network · Ford D1 BD-rate vs RENOBD-rate (%): -8.60Improved
add cross-bit-depth feature propagation (ablation)RENO-style coding network · SemanticKITTI D1 BD-rate vs RENOBD-rate (%): -6.61Improved
add cross-bit-depth feature propagation (ablation)RENO-style coding network · Runtimeencoding time ratio: 0.90x enc, 0.85x dec vs RENOImproved
add Bag-of-Encoders with K=3 (ablation)ELiC w/o BoE · Ford D1 BD-rateBD-rate (%): -1.31Improved
add Bag-of-Encoders with K=3 (ablation)ELiC w/o BoE · SemanticKITTI D1 BD-rateBD-rate (%): -2.89Improved
increase BoE pool size from K=5 to K=7 (ablation)ELiC · Ford D1 BD-rateBD-rate (%): -1.98 -> -1.43Hurt
increase BoE pool size from K=5 to K=6 (ablation)ELiC · SemanticKITTI D1 BD-rateBD-rate (%): -3.54 -> -3.53No clear effect
use 14 dedicated per-level networks instead of K=5 pool (ablation)ELiC · Ford D1 BD-rateBD-rate (%): -1.98 -> -2.52Improved
use Morton-order-preserving hierarchy instead of explicit per-level sorting (ablation)ELiC · Runtimeaverage encoding time (s): 0.142 -> 0.121Improved
use Morton-order-preserving hierarchy instead of explicit per-level sorting (ablation)ELiC · Runtimeaverage decoding time (s): 0.128 -> 0.111Improved
add asynchronous arithmetic encodingELiC · Runtimeaverage encoding time (s): 0.121 -> 0.106Improved
double feature channels (ELiC to ELiC-Large)ELiC · Ford D1 BD-rateBD-rate (%): -22.97 -> -26.54Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy