Adaptive Augmentation-Aware Latent Learning for Robust LiDAR Semantic Segmentation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910036927709184 |
|---|---|
| author | Li, Wangkai Li, Zhaoyang Pan, Yuwen Sun, Rui Chen, Yujia Zhang, Tianzhu |
| author_facet | Li, Wangkai Li, Zhaoyang Pan, Yuwen Sun, Rui Chen, Yujia Zhang, Tianzhu |
| contents | Adverse weather conditions significantly degrade the performance of LiDAR point cloud semantic segmentation networks by introducing large distribution shifts. Existing augmentation-based methods attempt to enhance robustness by simulating weather interference during training. However, they struggle to fully exploit the potential of augmentations due to the trade-off between minor and aggressive augmentations. To address this, we propose A3Point, an adaptive augmentation-aware latent learning framework that effectively utilizes a diverse range of augmentations while mitigating the semantic shift, which refers to the change in the semantic meaning caused by augmentations. A3Point consists of two key components: semantic confusion prior (SCP) latent learning, which captures the model's inherent semantic confusion information, and semantic shift region (SSR) localization, which decouples semantic confusion and semantic shift, enabling adaptive optimization strategies for different disturbance levels. Extensive experiments on multiple standard generalized LiDAR segmentation benchmarks under adverse weather demonstrate the effectiveness of our method, setting new state-of-the-art results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_01074 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Adaptive Augmentation-Aware Latent Learning for Robust LiDAR Semantic Segmentation Li, Wangkai Li, Zhaoyang Pan, Yuwen Sun, Rui Chen, Yujia Zhang, Tianzhu Computer Vision and Pattern Recognition Adverse weather conditions significantly degrade the performance of LiDAR point cloud semantic segmentation networks by introducing large distribution shifts. Existing augmentation-based methods attempt to enhance robustness by simulating weather interference during training. However, they struggle to fully exploit the potential of augmentations due to the trade-off between minor and aggressive augmentations. To address this, we propose A3Point, an adaptive augmentation-aware latent learning framework that effectively utilizes a diverse range of augmentations while mitigating the semantic shift, which refers to the change in the semantic meaning caused by augmentations. A3Point consists of two key components: semantic confusion prior (SCP) latent learning, which captures the model's inherent semantic confusion information, and semantic shift region (SSR) localization, which decouples semantic confusion and semantic shift, enabling adaptive optimization strategies for different disturbance levels. Extensive experiments on multiple standard generalized LiDAR segmentation benchmarks under adverse weather demonstrate the effectiveness of our method, setting new state-of-the-art results. |
| title | Adaptive Augmentation-Aware Latent Learning for Robust LiDAR Semantic Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.01074 |