兰萨克
可微函数
计算机科学
解算器
人工智能
采样(信号处理)
匹配(统计)
点云
特征(语言学)
计算机视觉
算法
机器学习
数学
图像(数学)
统计
数学分析
哲学
滤波器(信号处理)
语言学
程序设计语言
作者
Tong Wei,Yash Patel,Alexander Shekhovtsov,Jǐŕı Matas,Dániel Baráth
标识
DOI:10.1109/iccv51070.2023.01618
摘要
We propose ▽-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 ▽-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 ▽-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.
科研通智能强力驱动
Strongly Powered by AbleSci AI