CCF：面向域泛化多模态3D目标检测的互补协同融合
CCF: Complementary Collaborative Fusion for Domain Generalized Multi-Modal 3D Object Detection
针对双分支 proposal-level 多模态 3D 检测器，提出查询解耦损失、LiDAR 引导深度先验和互补跨模态掩码，可复用于提升视觉-激光雷达融合模型在恶劣域下的鲁棒性。
原文依据 focusing on dual-branch proposal-level detectors, we identify two factors that limit robust cross-domain generalization
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论多模态融合已成为实现精确3D目标检测的一种有前景的范式。然而，当部署在与训练域不同的目标域时，性能会显著下降。在本工作中，我们聚焦于双分支提案级检测器，识别出限制鲁棒跨域泛化的两个因素：1）在雨天或夜间等挑战性域中，某一模态可能发生严重退化；2）激光雷达分支通常在检测过程中占据主导地位，导致视觉线索被系统性低估，并在点云受损时表现出脆弱性。为解决这些挑战，我们提出三个组件。首先，查询解耦损失为仅2D、仅3D和融合查询提供独立监督，重新平衡跨模态的梯度流。其次，激光雷达引导深度先验通过概率融合图像预测和激光雷达导出的深度分布，为2D查询增强实例感知的几何先验，改善其空间初始化。第三，互补跨模态掩码对图像和点云施加互补的空间掩码，促使来自两种模态的查询在融合解码器内竞争，从而促进自适应融合。大量实验表明，在保持源域性能的同时，相较于最优基线取得了显著提升。代码和模型已公开于 https://github.com/IMPL-Lab/CCF.git。
英文原文摘要 1440 字符
Multi-modal fusion has emerged as a promising paradigm for accurate 3D object detection. However, performance degrades substantially when deployed in target domains different from training. In this work, focusing on dual-branch proposal-level detectors, we identify two factors that limit robust cross-domain generalization: 1) in challenging domains such as rain or nighttime, one modality may undergo severe degradation; 2) the LiDAR branch often dominates the detection process, leading to systematic underutilization of visual cues and vulnerability when point clouds are compromised. To address these challenges, we propose three components. First, Query-Decoupled Loss provides independent supervision for 2D-only, 3D-only, and fused queries, rebalancing gradient flow across modalities. Second, LiDAR-Guided Depth Prior augments 2D queries with instance-aware geometric priors through probabilistic fusion of image-predicted and LiDAR-derived depth distributions, improving their spatial initialization. Third, Complementary Cross-Modal Masking applies complementary spatial masks to the image and point cloud, encouraging queries from both modalities to compete within the fused decoder and thereby promoting adaptive fusion. Extensive experiments demonstrate substantial gains over state-of-the-art baselines while preserving source-domain performance. Code and models are publicly available at https://github.com/IMPL-Lab/CCF.git.