AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Semantic segmentation of sparse irregular point clouds for leaf/wood discrimination

Yuchen BAI, Jean-Baptiste Durand, Grégoire Laurent Vincent, Florence Forbes

NeurIPS 2023 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 3 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
rebalanced loss (random selection of leaf points) instead of focal loss (ablation)SOUL · French Guiana ULSspecificity: 0.395 -> 0.631Improved
rebalanced loss instead of focal loss (ablation)SOUL · French Guiana ULSG-mean: 0.615 -> 0.744Improved
rebalanced loss instead of focal loss (ablation)SOUL · French Guiana ULSbalanced accuracy: 0.677 -> 0.757Improved
rebalanced loss instead of focal loss (ablation)SOUL · French Guiana ULSaccuracy: 0.942 -> 0.826Hurt
multi-scale geometric features instead of linearity at one scale (ablation)SOUL · French Guiana ULSspecificity: 0.31 -> 0.631Improved
multi-scale geometric features instead of linearity at one scale (ablation)SOUL · French Guiana ULSbalanced accuracy: 0.636 -> 0.757Improved
multi-scale geometric features instead of linearity at one scale (ablation)SOUL · French Guiana ULSaccuracy: 0.962 -> 0.826Hurt
SOUL rebalanced loss vs FSCTSOUL · French Guiana ULSspecificity: 0.13 -> 0.631Improved
SOUL rebalanced loss vs LeWosSOUL · French Guiana ULSbalanced accuracy: 0.520 -> 0.757Improved
retrain FSCT on ULS dataFSCT · French Guiana ULSspecificity: 0.13 -> 0.01Hurt
95% confidence interval over 16 test sets for SOULSOUL · French Guiana ULSspecificity: 0.631 -> 0.576No clear effect
GVD spatial split instead of voxel or sliding-window partition (ablation)SOUL · French Guiana ULSborder noiseImproved

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