RANSAC and its variants are widely used for robust estimation, however, they commonly follow a greedy approach to finding the highest scoring model while ignoring other model hypotheses. In contrast, Iteratively Reweighted Least Squares (IRLS) techniques gradually approach the model by iteratively updating the weight of each correspondence based on the residuals from previous iterations. Inspired by these methods, we propose a new RANSAC framework that learns to explore the parameter space by considering the residuals seen so far via a novel attention layer. The attention mechanism operates on a batch of point-to-model residuals, and updates a per-point estimation state to take into account the consensus found through a lightweight one-step transformer. This rich state then guides the minimal sampling between iterations as well as the model refinement. We evaluate the proposed approach on essential and fundamental matrix estimation on a number of indoor and outdoor datasets. It outperforms state-of-the-art estimators by a significant margin adding only a small runtime overhead. Moreover, we demonstrate good generalization properties of our trained model, indicating its effectiveness across different datasets and tasks. The proposed attention mechanism and one-step transformer provide an adaptive behavior that enhances the performance of RANSAC, making it a more effective tool for robust estimation. Code is available at https://github.com/cavalli1234/CA-RANSAC.

翻译：RANSAC及其变体被广泛用于鲁棒估计，然而，它们通常采用贪心策略寻找最高评分模型，而忽略其他模型假设。相比之下，迭代重加权最小二乘（IRLS）技术通过根据先前迭代的残差迭代更新每个对应点的权重来逐步逼近模型。受这些方法的启发，我们提出了一种新的RANSAC框架，该框架通过一种新颖的注意力层，基于当前已观察到的残差来学习探索参数空间。该注意力机制作用于一批点对模型残差，并通过轻量级单步Transformer更新每个点的估计状态，以考虑已发现的共识。这一丰富的状态随后指导迭代间的最小采样以及模型优化。我们在室内外多个数据集上评估了所提方法在本质矩阵和基本矩阵估计中的性能。该方法以极小的运行时开销显著优于最先进的估计器。此外，我们展示了训练模型良好的泛化特性，表明其在不同数据集和任务中的有效性。所提出的注意力机制和单步Transformer提供了自适应行为，增强了RANSAC的性能，使其成为鲁棒估计更有效的工具。代码见https://github.com/cavalli1234/CA-RANSAC。