Dimensions overall score 9.0

GitHub Code Pulse

No public code linked for this paper yet.

• AW-MoE achieves approximately 15% improvement in adverse-weather performance over state-of-the-art methods.result 90%
• AW-MoE incurs negligible inference overhead while improving performance.technical 85%
• The Image-guided Weather-aware Routing (IWR) leverages image features' superior discriminability across weather conditions for precise weather classification.method 88%
• IWR selects the top-K most relevant Weather-Specific Experts (WSE) to handle data discrepancies across weather conditions.method 87%
• AW-MoE integrates Mixture of Experts (MoE) into weather-robust multi-modal 3D object detection approaches.method 95%
• The Unified Dual-Modal Augmentation (UDMA) provides synchronous LiDAR and 4D Radar dual-modal data augmentation while preserving scene realism.method 86%
• Integrating AW-MoE into established baseline detectors yields performance improvements surpassing current state-of-the-art methods.result 85%
• Most existing methods overlook data distribution discrepancies across different weather scenarios, leading to performance conflicts.limitation 82%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card