Deep Regression on Manifolds: A 3D Rotation Case Study
Many machine learning problems involve regressing variables on a non-Euclidean manifold -- e.g. a discrete probability distribution, or the 6D pose of an object. One way to tackle these problems through gradient-based learning is to use a differentiable function that maps arbitrary inputs of a Euclidean space onto the manifold. In this paper, we establish a set of desirable properties for such mapping, and in particular highlight the importance of pre-images connectivity/convexity. We illustrate these properties with a case study regarding 3D rotations. Through theoretical considerations and methodological experiments on a variety of tasks, we review various differentiable mappings on the 3D rotation space, and conjecture about the importance of their local linearity. We show that a mapping based on Procrustes orthonormalization generally performs best among the mappings considered, but that a rotation vector representation might also be suitable when restricted to small angles.
Code (1)
Tasks
regressionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Normalizing Flows on the Product Space of SO(3) Manifolds for Probabilistic Human Pose Modeling
Normalizing flows have proven their efficacy for density estimation in Euclidean space, but their application to rotational representations, crucial in various domains such as robotics or human pose modeling, remains und…
Density EstimationSpherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres
Many computer vision challenges require continuous outputs, but tend to be solved by discrete classification. The reason is classification's natural containment within a probability $n$-simplex, as defined by the popular…
3D Rotation EstimationregressionSurface Normal EstimationSurface Normals Estimation+1Projective Manifold Gradient Layer for Deep Rotation Regression
Regressing rotations on SO(3) manifold using deep neural networks is an important yet unsolved problem. The gap between the Euclidean network output space and the non-Euclidean SO(3) manifold imposes a severe challenge f…
regressionRiemannian optimizationRMLR: Extending Multinomial Logistic Regression into General Geometries
Riemannian neural networks, which extend deep learning techniques to Riemannian spaces, have gained significant attention in machine learning. To better classify the manifold-valued features, researchers have started ext…
regressionPSyCo: Manifold Span Reduction for Super Resolution
The main challenge in Super Resolution (SR) is to discover the mapping between the low- and high-resolution manifolds of image patches, a complex ill-posed problem which has recently been addressed through piecewise line…
regressionSuper-Resolution