CVLGROSep 11, 2025

DGFusion: Depth-Guided Sensor Fusion for Robust Semantic Perception

arXiv:2509.09828v13 citationsh-index: 27Has CodeIEEE Robot Autom Lett
Originality Highly original
AI Analysis

This addresses the challenge of reliable sensor fusion in autonomous vehicles under adverse conditions, representing an incremental improvement over existing fusion approaches.

The paper tackles the problem of robust semantic perception for autonomous vehicles by proposing a depth-guided sensor fusion method that dynamically adapts fusion based on spatially varying sensor reliability, achieving state-of-the-art panoptic and semantic segmentation performance on MUSES and DELIVER datasets.

Robust semantic perception for autonomous vehicles relies on effectively combining multiple sensors with complementary strengths and weaknesses. State-of-the-art sensor fusion approaches to semantic perception often treat sensor data uniformly across the spatial extent of the input, which hinders performance when faced with challenging conditions. By contrast, we propose a novel depth-guided multimodal fusion method that upgrades condition-aware fusion by integrating depth information. Our network, DGFusion, poses multimodal segmentation as a multi-task problem, utilizing the lidar measurements, which are typically available in outdoor sensor suites, both as one of the model's inputs and as ground truth for learning depth. Our corresponding auxiliary depth head helps to learn depth-aware features, which are encoded into spatially varying local depth tokens that condition our attentive cross-modal fusion. Together with a global condition token, these local depth tokens dynamically adapt sensor fusion to the spatially varying reliability of each sensor across the scene, which largely depends on depth. In addition, we propose a robust loss for our depth, which is essential for learning from lidar inputs that are typically sparse and noisy in adverse conditions. Our method achieves state-of-the-art panoptic and semantic segmentation performance on the challenging MUSES and DELIVER datasets. Code and models will be available at https://github.com/timbroed/DGFusion

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes