用脉冲相机增强视频显著性检测，消除噪声导致的偏差。
SOTA: Spike-Navigated Optimal TrAnsport Saliency Region Detection in Composite-bias Videos
- 基于脉冲信号微调帧间差异，保留细微变化细节
- 通过全局去偏机制减少不同条件下预测不一致
- 适合处理含运动模糊与遮挡的真实视频场景
现有显著性检测方法在真实场景中因运动模糊和遮挡表现不佳。相比之下，具有高时间分辨率的脉冲相机能显著提升视觉显著性图质量。然而，脉冲相机成像固有的复合噪声会引入显著性检测的不连续性，低质量样本进一步扭曲模型预测，造成显著性偏差。为此，我们提出脉冲导航最优传输显著区域检测（SOTA）框架，充分利用脉冲相机优势，同时在时空维度上缓解偏差。该方法引入基于脉冲的微去偏（SM），捕捉帧间细微变化，即使在场景或光照变化极小的情况下也能保留关键细节；此外，基于脉冲的全局去偏（SG）通过降低多种条件下的预测不一致性来优化结果。在真实与合成数据集上的大量实验表明，SOTA有效消除了复合噪声带来的偏差，优于现有方法。代码与数据集将公开于 https://github.com/lwxfight/sota。
原文摘要 · Abstract (English)
Existing saliency detection methods struggle in real-world scenarios due to motion blur and occlusions. In contrast, spike cameras, with their high temporal resolution, significantly enhance visual saliency maps. However, the composite noise inherent to spike camera imaging introduces discontinuities in saliency detection. Low-quality samples further distort model predictions, leading to saliency bias. To address these challenges, we propose Spike-navigated Optimal TrAnsport Saliency Region Detection (SOTA), a framework that leverages the strengths of spike cameras while mitigating biases in both spatial and temporal dimensions. Our method introduces Spike-based Micro-debias (SM) to capture subtle frame-to-frame variations and preserve critical details, even under minimal scene or lighting changes. Additionally, Spike-based Global-debias (SG) refines predictions by reducing inconsistencies across diverse conditions. Extensive experiments on real and synthetic datasets demonstrate that SOTA outperforms existing methods by eliminating composite noise bias. Our code and dataset will be released at https://github.com/lwxfight/sota.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。