AI Paper Atlas

Research map / Point clouds / Segmentation and detection

SLiDE: Self-Supervised LiDAR De-Snowing through Reconstruction Difficulty

Gwangtak Bae, Byungjun Kim, Seongyong Ahn, Jihong Min, Inwook Shim

ECCV 2022 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 25 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 multi-hypothesis learning (3 hypotheses) to PR-Net (ablation)Ours · Synthetic snow noise data (nuScenes base)IoU: 65.75 -> 79.62Improved
use 3 hypotheses instead of 2 (ablation)Ours · Synthetic snow noise data (nuScenes base)IoU: 76.17 -> 79.62Improved
use 4 hypotheses instead of 3 (ablation)Ours · Synthetic snow noise data (nuScenes base)IoU: 79.62 -> 76.52Hurt
blank 50% of points instead of 10% (ablation)Ours · Synthetic snow noise data (nuScenes base)IoU: 76.64 -> 79.62Improved
blank 70% instead of 50% (ablation)Ours · Synthetic snow noise data (nuScenes base)IoU: 79.62 -> 76.57Hurt
use 20th percentile shift instead of minimum output (ablation)Ours · Synthetic snow noise data (nuScenes base)IoU: 72.63 -> 79.62Improved
use 20th percentile shift instead of 10th (ablation)Ours · Synthetic snow noise data (nuScenes base)IoU: 79.36 -> 79.62No clear effect
add semi-supervised extension with 239 labels vs WeatherNetOurs Semi-sup · Synthetic snow noise data (nuScenes base)IoU: 41.40 -> 82.44Improved
add semi-supervised extension at full labelsOurs Semi-sup · Synthetic snow noise data (nuScenes base)IoU: 84.04 -> 84.24No clear effect
use pretrain weighting instead of smooth transfer at 1% labels (ablation)Semi-supervised · Synthetic snow noise data (nuScenes base) (1% labels)IoU: 82.44 -> 62.46Hurt
use ramp up/down weighting at 100% labels instead of supervised only (ablation)Semi-supervised · Synthetic snow noise data (nuScenes base) (100% labels)IoU: 84.04 -> 82.57Hurt
use label-free method vs DROROurs · Synthetic snow noise data (nuScenes base)IoU: 33.68 -> 79.62Improved

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