AI Paper Atlas

Research map / Point clouds / Point cloud classification

BitRIC: Efficient Neural Compression of LiDAR Range Images via Hierarchical Bitplanes

Kang You, Tong Chen, Dandan Ding, M. Salman Asif, Zhan Ma

ECCV 2026 · Point clouds › Point cloud classification · approach: LiDAR point cloud compression and completion · 0 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 range embedding (ablation)BitRIC · WODBD-BR D1: -16.26% -> -61.73%Improved
add positional embedding (ablation)BitRIC · WODBD-BR D1: -60.37% -> -61.73%Improved
add horizontal folding (ablation)BitRIC · WODFLOPs per bitplane: 144.55G -> 27.78GImproved
add U-Net-based aggregation (ablation)BitRIC · WODBD-BR D1: -45.06% -> -61.73%Improved
fold along horizontal instead of vertical axis (ablation)BitRIC · WODBD-BR D1: -50.28% -> -61.73%Improved
increase folding ratio from 4 to 8 (ablation)BitRIC · WODBD-BR D1: -61.73% -> -54.83%Hurt
increase folding ratio from 1 to 4 (ablation)BitRIC · WODBD-BR D1: -61.43% -> -61.73%No clear effect
increase PEM stages from 1 to 3 (ablation)BitRIC · WODBD-BR D1: -24.27% -> -61.73%Improved
increase PEM stages from 3 to 4 (ablation)BitRIC · WODBD-BR D1: -61.73% -> -61.90%No clear effect
add one-step refinement module (ORM) (ablation)BitRIC · WODD1 PSNR / Chamfer distance at 2.528 Bpp: 68.96dB -> 71.58dB; 0.062m -> 0.042mImproved
evaluate WOD-trained model zero-shot on SemanticKITTI (ablation)BitRIC · SemanticKITTIBD-BR D1: 69.92% -> 56.93%Mixed
use BitRIC instead of RPCC at ~2 Bpp for detectionBitRIC vs RPCC · WOD pedestrian Level 1 detectionmAP: 58.95 -> 65.67Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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