AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Towards Real-Time Full-Waveform LiDAR Transformers via Intensity-Guided Token Reduction and Physics-Aware Augmentation

Kazuma Ikeda, Kotaro Oishi, Ryosei Hara, Ryo Yoshida, Mariko Isogawa, Kazuma Ikeda

NeurIPS 2026 · Architectures and efficiency › Attention and transformers · approach: Efficient and robust vision transformers · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a real-time Transformer for full-waveform LiDAR that uses intensity-guided token reduction and physics-aware augmentation (abstract only available).

Problem

Full-waveform LiDAR captures rich return signals robust to adverse conditions, but Transformer-based FWL models are computationally expensive for real-time use.

Approach

Reduces Transformer tokens using LiDAR return intensity as guidance and adds physics-aware data augmentation to FWL inputs; the abstract does not give further detail.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Replace prior SOTA (Ikeda et al.) with FWL-ToPMFWL Transformer · Ghost-FWLF1-mean and FPS: 0.503 -> 0.592 F1; 6.54 -> 53.2 FPSImproved
Add intensity-based token pruning (rho_low=0.7) (ablation)Ours w/o FWL-ToPM · Ghost-FWLF1-mean: 0.555 -> 0.591Improved
Add sparse-aware token merging (ablation)Ours w/o FWL-ToPM · Ghost-FWLF1-mean: 0.555 -> 0.565Improved
Combine pruning and merging (ablation)FWL-ToPM · Ghost-FWLF1-mean and FPS: 20.3 FPS (pruning only) -> 53.2 FPS, F1 0.591 -> 0.592Improved
Use proposed pruning instead of DynamicViT (ablation)Token pruning · Ghost-FWLF1-mean: 0.480 -> 0.591Improved
Use proposed merging instead of ToMe (ablation)Token merging · Ghost-FWLF1-mean: 0.543 -> 0.565Improved
Increase pruning ratio to reach about 80 FPS (ablation)Pruning only · Ghost-FWLF1-meanHurt
Apply token pruning to a pretrained model without retraining (ablation)FWL-ToPM · Ghost-FWLF1-meanHurt
Apply token merging to a pretrained model without retraining (ablation)FWL-ToPM · Ghost-FWLF1-meanNo clear effect
Add FWLAug (CutMix + ShiftMix) (ablation)FWL-ToPM · OOD testF1-mean: 0.406 -> 0.452Improved
Add FWLAug (CutMix + ShiftMix) (ablation)FWL-ToPM · OOD test Glass classF1: 0.491 -> 0.575Improved
Add FWLCutMix only without ShiftMix (ablation)FWL-ToPM · Ghost-FWLF1-mean: 0.592 -> 0.586Hurt

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