DiffSAC：用于基于共识的鲁棒估计的扩散引导采样
DiffSAC: Diffusion-guided Sampling for Consensus-based Robust Estimation
- School of Automation and Intelligent Sensing, Shanghai Jiao Tong University（上海交通大学自动化与智能感知学院）
- Key Laboratory of System Control and Information Processing, Ministry of Education of China（教育部系统控制与信息处理重点实验室）
- Department of Engineering, Cambridge University（剑桥大学工程系）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
针对传统样本共识鲁棒估计采样效率低的问题，提出DiffSAC框架，通过扩散模型学习有效最小集分布，仅需几十个假设就实现最先进性能，可作为即插即用模块改进现有方法。
中文摘要 AI 辅助
鲁棒估计是核心计算机视觉任务，常采用样本共识方法解决，但传统方法存在采样效率低下的问题，因为它们在假设评估前难以识别有效最小集。为应对这些挑战，我们提出了一种新颖的用于基于共识的鲁棒估计的扩散引导采样框架DiffSAC。DiffSAC引入扩散模型来学习有效最小集的分布，它对每个数据点的置信度进行细化，指示其是否属于良好的最小集，而非像以往工作那样对数据点进行排名，这大幅减少了处理大量不良集的需求。为约束细化方向，我们将几何特征作为条件融入扩散模型中。因此，DiffSAC输出少量高质量的最小集，可通过共识评估识别最佳假设。值得注意的是，与以往需要评估超过一万个假设的工作相比，DiffSAC仅需几十个假设就达到了最先进的性能，显著提升了效率。在五个经典计算机视觉任务上进行的大量实验证明了DiffSAC的优越性。该扩散模型的采样加速器支持实时运行，且DiffSAC可作为即插即用模块用于改进现有的样本共识方法。
英文摘要
Robust estimation is a core computer vision task frequently tackled using sample consensus. However, traditional methods suffer from inefficient sampling as they struggle to identify effective minimum sets before hypothesis evaluation. To address these challenges, we propose a novel Diffusion-guided Sampling for Consensus-based Robust Estimation (DiffSAC) framework. DiffSAC introduces a diffusion model to learn the distribution of effective minimum sets. It refines the confidence for each data point, indicating whether it belongs to a good minimum set, rather than ranking the data points as in previous work. This significantly reduces the need to process numerous bad sets. To constrain the refinement direction, geometric features are incorporated as conditions within our diffusion model. Consequently, DiffSAC outputs a small number of high-quality minimum sets, enabling identification of the best hypothesis via consensus evaluation. Notably, compared to previous works requiring evaluating over ten thousand hypotheses, DiffSAC achieves state-of-the-art performance with only dozens, significantly boosting efficiency. Extensive experiments across five classic computer vision tasks demonstrate the superiority of DiffSAC. The diffusion model's sampling accelerators enable real-time operation, and DiffSAC can be used as a plug-and-play module to improve existing sample consensus methods.
