Estimating the 3DoF rotation from a single RGB image is an important yet challenging problem. Probabilistic rotation regression has raised more and more attention with the benefit of expressing uncertainty information along with the prediction. Though modeling noise using Gaussian-resembling Bingham distribution and matrix Fisher distribution is natural, they are shown to be sensitive to outliers for the nature of quadratic punishment to deviations. In this paper, we draw inspiration from multivariate Laplace distribution and propose a novel Rotation Laplace distribution on SO(3). Rotation Laplace distribution is robust to the disturbance of outliers and enforces much gradient to the low-error region, resulting in a better convergence. Our extensive experiments show that our proposed distribution achieves state-of-the-art performance for rotation regression tasks over both probabilistic and non-probabilistic baselines. Our project page is at https://pku-epic.github.io/RotationLaplace.

翻译：从单张RGB图像估计3自由度旋转是一个重要且具有挑战性的问题。概率旋转回归因能在预测的同时表达不确定性信息而受到越来越多的关注。尽管使用类高斯Bingham分布和矩阵Fisher分布对噪声进行建模是自然的，但因其对偏差进行二次惩罚的特性，它们对异常值较为敏感。本文从多元拉普拉斯分布中汲取灵感，提出了一种新颖的SO(3)旋转拉普拉斯分布。旋转拉普拉斯分布对异常值的干扰具有鲁棒性，并向低误差区域施加更多梯度，从而获得更好的收敛性。我们的大量实验表明，所提出的分布在概率与非概率基线上均实现了旋转回归任务的最优性能。我们的项目页面位于https://pku-epic.github.io/RotationLaplace。