AI Paper Atlas

Research map / Point clouds / Point cloud classification

PACE: Post-Causal Entropy Modeling for Learned LiDAR Point Cloud Compression

Jiahao Zhu, Kang You, Dandan Ding, Zhan Ma

ICML 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 graph-based positional encoding (ablation)PACE-FP · FordBD-BR (%): -38.22% -> -50.19%Improved
add graph-based positional encoding (ablation)PACE-AR · FordBD-BR (%): -46.14% -> -55.07%Improved
use post-causal instead of fully-causal modeling (ablation)PACE-AR · FordBD-BR (%): -52.34% -> -55.07%Improved
use post-causal instead of fully-causal modeling (ablation)PACE-AR · Forddecoding latency at L=14: ~90x slower for fully-causalImproved
increase decoding stages from 1 to 16 (ablation)PACE · FordBD-BR (%): -50.19% -> -54.23%Improved
increase decoding stages from 1 to 16 (ablation)PACE · Forddecoding time (s): 1.55 s -> 2.18 sHurt
use Mamba predictor instead of MLP (ablation)PACE-AR · FordBD-BR (%): -52.49% -> -55.07%Improved
use Mamba predictor instead of Attention (ablation)PACE-AR · FordBD-BR / memory / decoding: -54.83% -> -55.07%, 2.68GB -> 0.58GB, 40.95s -> 16.36sMixed
use joint predictor instead of separate predictors (ablation)PACE-FP · FordBD-BR (%): -50.68% -> -50.19%No clear effect
use joint predictor instead of separate predictors (ablation)PACE-AR · FordBD-BR (%): -55.93% -> -55.07%No clear effect
use intrinsic-aware preprocessing instead of spherical or Cartesian octree (ablation)PACE · FordBD-BR (%)Improved
reduce point density by downsampling 4xPACE-FP vs L3C2 · FordBD-BR (%): -50.19% -> -30.00% (L3C2 -45.67% -> -29.79%)Hurt

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