AI Paper Atlas

Research map / Point clouds / Point cloud classification

Towards Practical Lossless Neural Compression for LiDAR Point Clouds

pengpeng yu, Haoran Li, Runqing Jiang, Dingquan Li, Jing Wang, Liang Lin, Yulan Guo

ECCV 2026 · Point clouds › Point cloud classification · approach: LiDAR point cloud compression and completion · 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 GRED to the baseline octree codec (ablation)Baseline · KITTI D1BD-Rate vs Baseline (%): 0.00 -> -3.78Improved
add GRED to the baseline octree codec (ablation)Baseline · KITTI D1BD-PSNR vs Baseline (dB): 0.00 -> 0.40Improved
add XFP on top of GRED (ablation)Baseline + GRED · KITTI D1BD-Rate vs Baseline (%): -3.78 -> -13.22Improved
add XFP on top of GRED (ablation)Baseline + GRED · KITTI D1BD-PSNR vs Baseline (dB): 0.40 -> 1.46Improved
add XFP on top of GRED (ablation)Baseline + GRED · KITTI D1BD-Rate vs G-PCC octree (%): -13.44 -> -21.93Improved
add GRED to the baseline octree codec (ablation)Baseline · KITTI D1BD-Rate vs G-PCC octree (%): -10.04 -> -13.44Improved
add GRED to the baseline octree codec (ablation)Baseline · KITTI D1BD-PSNR vs G-PCC octree (dB): 1.13 -> 1.49Improved
use integer-only inference instead of floating pointOurs · KITTI D1BD-Rate vs RENO (%): -15.582 -> -14.289Mixed
use integer-only inference instead of floating pointOurs · Ford D1BD-Rate vs RENO (%): -11.049 -> -6.875Hurt
use integer-only inference instead of floating pointOurs · KITTI encoding time (RTX 4090)encoding time (s): 0.075s -> 0.060sImproved
run integer model on RTX 5880 instead of RTX 4090Ours (Integer) · KITTI encoding timeencoding time (s): 0.060s -> 0.047sImproved
run integer model on Tesla V100 instead of RTX 4090Ours (Integer) · KITTI encoding timeencoding time (s): 0.060s -> 0.166sHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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