AI Paper Atlas

Research map / Point clouds / Shape and surface completion

ESNE: Efficient Surface Normal Estimation for LiDAR Point Clouds with Sequential Modeling and Variability Guidance

Kohei Matsuzaki, Keisuke Nonaka

ECCV 2026 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 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
replace LiSu method with ESNELiSu baseline · LiSumean angular error (deg): 6.26 -> 4.17Improved
replace LiSu method with ESNELiSu baseline · LiSuinference time (s): 0.08 -> 0.04Improved
add SLA and VFR on top of SSM (ablation)ESNE · LiSumean angular error (deg): 5.38 -> 4.17Improved
add VFR (ablation)ESNE · LiSumean angular error (deg): 4.29 -> 4.17Improved
add SSM (ablation)ESNE · LiSumean angular error (deg): 4.33 -> 4.17Improved
use spatial k-NN instead of sequential k-NN (ablation)ESNE · LiSumean angular error (deg): 4.17 -> 3.70Improved
use spatial k-NN instead of sequential k-NN (ablation)ESNE · LiSuinference time (ms): 41.5 -> 495.2Hurt
increase SLA neighbours k from 3 to 15 (ablation)ESNE · LiSumean angular error (deg): 5.04 -> 4.03Improved
increase k from 9 to 15 (ablation)ESNE · LiSuinference time (ms): 41.5 -> 51.0Hurt
use Z-order instead of Hilbert serialization (ablation)ESNE · LiSumean angular error (deg): 4.17 -> 4.23No clear effect
add noise sigma 0.01 to test setESNE · LiSumean angular error (deg): 4.17 -> 4.32Hurt
use ESNE normals for NKSR reconstruction instead of LiSu normalsNKSR · CARLA (Original)CD-L1: 0.0362 -> 0.0357Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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