CoopDiff：一种面向退化条件下协同的扩散引导方法
CoopDiff: A Diffusion-Guided Approach for Cooperation under Corruptions
把扩散去噪器当作特征级净化模块，用教师-学生范式在体素早期融合阶段生成干净监督，并用自我引导交叉注意力在退化条件下平衡融合两路特征；做车路协同/多智能体感知且需应对传感器与环境退化时可直接借鉴该去噪-融合结构。
原文依据 CoopDiff adopts a teacher-student paradigm: the Quality-Aware Teacher performs voxel-level early fusion with Quality of Interest weighting and semantic guidance
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论协同感知使智能体能够共享信息以扩大覆盖范围并提升场景理解能力。然而在真实场景中，多样且不可预测的退化会削弱其鲁棒性与泛化能力。为应对这些挑战，我们提出 CoopDiff，一个基于扩散的协同感知框架，通过去噪机制缓解退化影响。CoopDiff 采用教师-学生范式：质量感知教师以兴趣质量加权与语义引导进行体素级早期融合，随后通过扩散去噪器生成干净的监督特征。双分支扩散学生先在编码阶段分离自车流与协同流，以重建教师的干净目标；随后，自我引导交叉注意力机制通过自适应整合自车特征与协同特征，在退化条件下实现均衡解码。我们在两个构建的多退化基准 OPV2Vn 与 DAIR-V2Xn 上评估 CoopDiff，二者各包含六种退化类型，涵盖环境层面与传感器层面的失真。得益于扩散固有的去噪特性，CoopDiff 在所有退化类型上均持续优于先前方法，并降低了相对退化误差。此外，它还在精度与推理效率之间提供了可调的平衡。
英文原文摘要 1350 字符
Cooperative perception lets agents share information to expand coverage and improve scene understanding. However, in real-world scenarios, diverse and unpredictable corruptions undermine its robustness and generalization. To address these challenges, we introduce CoopDiff, a diffusion-based cooperative perception framework that mitigates corruptions via a denoising mechanism. CoopDiff adopts a teacher-student paradigm: the Quality-Aware Teacher performs voxel-level early fusion with Quality of Interest weighting and semantic guidance, then produces clean supervision features via a diffusion denoiser. The Dual-Branch Diffusion Student first separates ego and cooperative streams in encoding to reconstruct the teacher's clean targets. And then, an Ego-Guided Cross-Attention mechanism facilitates balanced decoding under degradation by adaptively integrating ego and cooperative features. We evaluate CoopDiff on two constructed multi-degradation benchmarks, OPV2Vn and DAIR-V2Xn, each incorporating six corruption types, including environmental and sensor-level distortions. Benefiting from the inherent denoising properties of diffusion, CoopDiff consistently outperforms prior methods across all degradation types and lowers the relative corruption error. Furthermore, it offers a tunable balance between precision and inference efficiency.