paper-with-me

홈 › Papers

Deep Regression on Manifolds: A 3D Rotation Case Study

2021-03-30 · Romain Brégier

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.

📄 PDF Abstract BibTeX arXiv:2103.16317

Code (1)

naver/roma 공식 구현 pytorch

Tasks

regression

Methods 이 논문이 사용한 방법론

Procrustes Procrustes

Similar Papers 제목 키워드 기반

Normalizing Flows on the Product Space of SO(3) Manifolds for Probabilistic Human Pose Modeling

2024-04-08 · CVPR 2024 1 · Olaf Dünkel, Tim Salzmann, Florian Pfaff

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 Estimation

Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres

2019-04-10 · CVPR 2019 6 · Shuai Liao, Efstratios Gavves, Cees G. M. Snoek

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+1

Projective Manifold Gradient Layer for Deep Rotation Regression

2021-10-22 · CVPR 2022 1 · Jiayi Chen, Yingda Yin, Tolga Birdal, Baoquan Chen 외

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 optimization

RMLR: Extending Multinomial Logistic Regression into General Geometries

2024-09-28 · Ziheng Chen, Yue Song, Rui Wang, XiaoJun Wu 외

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…

regression

PSyCo: Manifold Span Reduction for Super Resolution

2016-06-01 · CVPR 2016 6 · Eduardo Perez-Pellitero, Jordi Salvador, Javier Ruiz-Hidalgo, Bodo Rosenhahn

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