FWL-ToPM 如何透過強度引導 Token 精簡及物理感知增強,實現即時全波形 LiDAR Transformer
Towards Real-Time Full-Waveform LiDAR Transformers via Intensity-Guided Token Reduction and Physics-Aware Augmentation
FWL-ToPM 以強度引導的 Token 精簡與合併,配合 FWLAug 的波形保留式數據增強,提升全波形 LiDAR Transformer 的速度、準確度及泛化能力。在 Ghost-FWL benchmark 上,FWL-ToPM 提速超過 8 倍,F1 分數較先前最佳水平提升近 9 點。程式碼及分佈外(OOD)數據集已公開。
Published on Nov 5
Authors:
,
,
,
,
Abstract
A token pruning and merging mechanism and a waveform-preserving augmentation improve a full-waveform LiDAR Transformer to real-time speed and higher accuracy with better generalization.
LiDAR is a critical sensor for autonomous driving and robotics, yet it remains vulnerable to adverse conditions such as fog, rain, transparent objects, and low-reflectance surfaces. Full-waveform LiDAR (FWL) addresses these limitations by capturing the complete return waveform as a histogram, preserving rich reflection characteristics including multi-path echoes and weak signals. While recent Transformer-based approaches have demonstrated promise on FWL data, two fundamental bottlenecks remain: high computational cost from redundant tokens in low-intensity background regions, and limited generalization due to scarce annotated training data. We address both bottlenecks by exploiting the physical structure inherent to FWL data. First, we propose FWL-ToPM, a token pruning and merging mechanism that leverages intensity distributions to selectively reduce tokens while retaining critical waveform content. Second, we introduce FWLAug, a data augmentation framework designed as a regularization method that preserves waveform structure, retaining the Time-of-Flight waveform of each ray and the frustum geometry, to improve generalization to unseen scenes. Evaluated on the Ghost-FWL benchmark, FWL-ToPM achieves over 8 times speedup at real-time throughput alongside a nearly 9-point F1 gain over the prior state of the art, establishing the first real-time FWL Transformer that simultaneously improves accuracy. FWLAug further improves performance on both the standard benchmark and an out-of-distribution test set of unseen scenes. Together, these methods push FWL-based perception toward practical deployment. The code and the OOD dataset are publicly available and can be accessed via the project page: https://keio-csg.github.io/FWL-ToPM
View arXiv page View PDF Project page GitHub 4 Add to collection
Get this paper in your agent:
hf papers read 2611.07613
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.07613 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.07613 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.07613 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co