发表机构
FZI Research Center for Information Technology; Karlsruhe Institute of Technology（FZI信息技术研究中心; 卡尔斯鲁厄理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对异步协同感知中特征延迟与不完整问题，提出时间残差瓶颈方法，以姿态扭曲特征为锚点，用Δ t 条件 xLSTM 提取残差并门控修正，在 DAIR-V2X 和 OPV2V 上显著提升鲁棒性。
AI 中文摘要
协同感知扩展了自动驾驶汽车的感知范围，但当共享特征到达时出现延迟或不完整时，其性能会下降。大多数延迟鲁棒方法通过流引导对齐或直接特征传输来补偿延迟的协作者特征。在这项工作中，我们将异步协同感知表述为时间残差预测。我们的时间残差瓶颈将确定性的姿态扭曲协作者特征作为保守锚点，并使用条件于Δ t 的 xLSTM 从可用历史中提取时间残差证据。随后，面向检测器的残差瓶颈在自车融合前仅应用门控、正则化的修正，从而降低在时间对应不确定时覆盖可靠静态结构的风险。在 DAIR-V2X 和 OPV2V 上的实验表明，我们的方法在严重固定/不规则延迟和数据包丢失下尤其有效。在 DAIR-V2X 上，报告的检查点在同步峰值精度上做出少量牺牲，以换取在更强通信退化下的更好鲁棒性。受控诊断进一步表明，直接特征传输具有理想的上限，但在没有准确对应关系部署时可能变得不可靠。这些结果支持时间残差融合作为异步和不完整协同感知的实用替代方案。代码将在该 https URL 公开。
英文摘要
Collaborative perception extends the sensing range of autonomous vehicles, but its performance degrades when shared features arrive stale or incomplete. Most latency-robust methods compensate delayed collaborator features through flow-guided alignment or direct feature transport. In this work, we formulate asynchronous collaborative perception as temporal residual prediction. Our Temporal Residual Bottleneck keeps a deterministic pose-warped collaborator feature as a conservative anchor and uses a $Δt$-conditioned xLSTM to extract residual temporal evidence from the available history. A detector-facing residual bottleneck then applies only gated, regularized corrections before ego-side fusion, reducing the risk of overwriting reliable static structure when temporal correspondence is uncertain. Experiments on DAIR-V2X and OPV2V show that our method is especially effective under severe fixed/irregular delays and packet drops. On DAIR-V2X, the reported checkpoint trades a small amount of synchronized peak accuracy for better robustness under stronger communication degradation. Controlled diagnostics further indicate that direct feature transport has oracle headroom but can become unreliable when deployed without accurate correspondence. These results support temporal residual fusion as a practical alternative for asynchronous and incomplete collaborative perception. Code will be publicly released at https://url.fzi.de/8dk38.
CommentsAccepted to ACCV 2026
