广义可微RANSAC
Generalized Differentiable RANSAC
AI总结：
提出广义可微RANSAC（$\ abla$-RANSAC），通过松弛技术估计梯度并经可微求解器传播，优化采样分布以提升鲁棒估计精度，在多种视觉任务中优于现有方法且保持高效。
摘要：
我们提出了$\ abla$-RANSAC，一种广义可微RANSAC，允许学习整个随机鲁棒估计流程。该方法采用松弛技术估计采样分布中的梯度，并通过可微求解器进行传播。可训练的质量函数通过对$\ abla$-RANSAC中估计的所有模型得分进行边缘化，指导网络学习准确的内点概率或训练特征检测与匹配网络。该方法直接最大化抽取优质假设的概率，从而学习更好的采样分布。我们在基础矩阵和本质矩阵估计及3D点云配准等真实场景中测试了$\ abla$-RANSAC，涵盖室内外及手工与学习特征。其在精度上优于现有技术，运行速度与精度较低的替代方案相当。代码和模型见https://github.com/weitong8591/differentiable_ransac。
英文摘要：
We propose $\nabla$-RANSAC, a generalized differentiable RANSAC that allows learning the entire randomized robust estimation pipeline. The proposed approach enables the use of relaxation techniques for estimating the gradients in the sampling distribution, which are then propagated through a differentiable solver. The trainable quality function marginalizes over the scores from all the models estimated within $\nabla$-RANSAC to guide the network learning accurate and useful inlier probabilities or to train feature detection and matching networks. Our method directly maximizes the probability of drawing a good hypothesis, allowing us to learn better sampling distributions. We test $\nabla$-RANSAC on various real-world scenarios on fundamental and essential matrix estimation, and 3D point cloud registration, outdoors and indoors, with handcrafted and learning-based features. It is superior to the state-of-the-art in terms of accuracy while running at a similar speed to its less accurate alternatives. The code and trained models are available at https://github.com/weitong8591/differentiable_ransac.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
