# Weather-Conditioned Branch Routing for Robust LiDAR-Radar 3D Object Detection

arXiv: https://arxiv.org/abs/2604.05405 · HTML: https://mlsanity.com/paper/2604.05405/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 61 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 30 of 31)

- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [FUTR3D: A Unified Sensor Fusion Framework for 3D Detection](https://mlsanity.com/paper/2203.10642/) (2022)
- [EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection](https://mlsanity.com/paper/2007.08856/) (2020)
- [MVX-Net: Multimodal VoxelNet for 3D Object Detection](https://mlsanity.com/paper/1904.01649/) (2019)
- [Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather](https://mlsanity.com/paper/2108.05249/) (2021)
- [SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation](https://mlsanity.com/paper/2108.06709/) (2021)
- [LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion](https://mlsanity.com/paper/2303.03595/) (2023)
- [Sparse 3D convolutional neural networks](https://mlsanity.com/paper/1505.02890/) (2015)
- [MixGen: A New Multi-Modal Data Augmentation](https://mlsanity.com/paper/2206.08358/) (2022)
- [MapNav: A Novel Memory Representation via Annotated Semantic Maps for Vision-and-Language Navigation](https://mlsanity.com/paper/2502.13451/) (2025)
- [MiMo-Embodied: X-Embodied Foundation Model Technical Report](https://mlsanity.com/paper/2511.16518/) (2025)
- [MVFusion: Multi-View 3D Object Detection with Semantic-aligned Radar and Camera Fusion](https://mlsanity.com/paper/2302.10511/) (2023)
- [Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection](https://mlsanity.com/paper/2306.01438/) (2023)
- [Is Your HD Map Constructor Reliable under Sensor Corruptions?](https://mlsanity.com/paper/2406.12214/) (2024)
- [MapFusion: A Novel BEV Feature Fusion Network for Multi-modal Map Construction](https://mlsanity.com/paper/2502.04377/) (2025)
- [RoboAfford++: A Generative AI-Enhanced Dataset for Multimodal Affordance Learning in Robotic Manipulation and Navigation](https://mlsanity.com/paper/2511.12436/) (2025)
- [MSC-Bench: Benchmarking and Analyzing Multi-Sensor Corruption for Driving Perception](https://mlsanity.com/paper/2501.01037/) (2025)
- [Video-CoT: A Comprehensive Dataset for Spatiotemporal Understanding of Videos Based on Chain-of-Thought](https://mlsanity.com/paper/2506.08817/) (2025)
- [NavA3: Understanding Any Instruction, Navigating Anywhere, Finding Anything](https://mlsanity.com/paper/2508.04598/) (2025)
- [HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots](https://mlsanity.com/paper/2503.09010/) (2025)
- [Multi-Floor Zero-Shot Object Navigation Policy](https://mlsanity.com/paper/2409.10906/) (2024)
- [Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigation](https://mlsanity.com/paper/2511.13269/) (2025)
- [RTNH+: Enhanced 4D Radar Object Detection Network using Combined CFAR-based Two-level Preprocessing and Vertical Encoding](https://mlsanity.com/paper/2310.17659/) (2023)
- [What Really Matters for Robust Multi-Sensor HD Map Construction?](https://mlsanity.com/paper/2507.01484/) (2025)
- [TopoNav: Topological Graphs as a Key Enabler for Advanced Object Navigation](https://mlsanity.com/paper/2509.01364/) (2025)
- [MoE3D: Mixture of Experts meets Multi-Modal 3D Understanding](https://mlsanity.com/paper/2511.22103/) (2025)
- [SocialNav-Map: Dynamic Mapping with Human Trajectory Prediction for Zero-Shot Social Navigation](https://mlsanity.com/paper/2511.12232/) (2025)
- [Team Xiaomi EV-AD VLA: Caption-Guided Retrieval System for Cross-Modal Drone Navigation -- Technical Report for IROS 2025 RoboSense Challenge Track 4](https://mlsanity.com/paper/2510.02728/) (2025)
- [The RoboSense Challenge: Sense Anything, Navigate Anywhere, Adapt Across Platforms](https://mlsanity.com/paper/2601.05014/) (2026)

## Built on by (most cited first, 1 of 1)

- [FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation](https://mlsanity.com/paper/2606.30367/) (2026)

## Abstract (arXiv)

Robust 3D object detection in adverse weather is highly challenging due to the varying reliability of different sensors. While existing LiDAR-4D radar fusion methods improve robustness, they predominantly rely on fixed or weakly adaptive pipelines, failing to dy-namically adjust modality preferences as environmental conditions change. To bridge this gap, we reformulate multi-modal perception as a weather-conditioned branch routing problem. Instead of computing a single fused output, our framework explicitly maintains three parallel 3D feature streams: a pure LiDAR branch, a pure 4D radar branch, and a condition-gated fusion branch. Guided by a condition token extracted from visual and semantic prompts, a lightweight router dynamically predicts sample-specific weights to softly aggregate these representations. Furthermore, to prevent branch collapse, we introduce a weather-supervised learning strategy with auxiliary classification and diversity regularization to enforce distinct, condition-dependent routing behaviors. Extensive experiments on the K-Radar benchmark demonstrate that our method achieves state-of-the-art performance. Furthermore, it provides explicit and highly interpretable insights into modality preferences, transparently revealing how adaptive routing robustly shifts reliance between LiDAR and 4D radar across diverse adverse-weather scenarios. The source code with be released.