Search papers, labs, and topics across Lattice.
This paper introduces Dual-Critic Guided Diffusion Alignment (DCDA), a novel framework for robust 3D object detection that addresses the challenges posed by varying weather conditions in autonomous driving. By leveraging a 4D radar-conditioned diffusion process and two complementary critics鈥攐ne focused on detection accuracy and the other on distributional consistency鈥擠CDA effectively refines degraded LiDAR features without relying on specific weather modeling. Experimental results demonstrate that DCDA significantly outperforms existing methods in unseen weather scenarios, showcasing its potential for real-world applications in autonomous systems.
DCDA achieves robust 3D object detection under diverse weather conditions by aligning degraded LiDAR features to a clean manifold without needing explicit weather labels.
Robust 3D object detection under adverse weather remains a critical hurdle for autonomous driving. Despite progress with LiDAR-4D radar fusion, most methods are constrained by a closed-world assumption, implicitly requiring training and test weather to align in both type and severity. This premise fails in practice: the open-ended nature of weather, and even variations within a single type like rain, cause dramatically different LiDAR degradation patterns, leading to significant performance drops in unseen conditions. To address this, we present Dual-Critic Guided Diffusion Alignment (DCDA), a weather-agnostic framework that learns to recover degraded LiDAR features toward a clean manifold. Rather than modeling specific weather types, DCDA employs a 4D radar-conditioned diffusion process to progressively refine features, guided by two complementary critics. (i) A detection-guided critic, anchored by a pre-trained clean-weather model, ensures that the refined features retain object-level discriminability and localization accuracy. (ii) A weather adversarial critic enforces holistic distributional consistency with clean-weather representations. By aligning features through semantic and distributional constraints rather than explicit weather modeling, DCDA generalizes effectively to unseen weather types and severities without requiring paired data or weather labels. We further introduce a structured open-weather benchmark with held-out type-severity combinations and extensive experiments verify DCDA's advantages.
