Recent interest in point cloud analysis has led rapid progress in designing deep learning methods for 3D models. However, state-of-the-art models are not robust to rotations, which remains an unknown prior to real applications and harms the model performance. In this work, we introduce a novel Patch-wise Rotation-invariant network (PaRot), which achieves rotation invariance via feature disentanglement and produces consistent predictions for samples with arbitrary rotations. Specifically, we design a siamese training module which disentangles rotation invariance and equivariance from patches defined over different scales, e.g., the local geometry and global shape, via a pair of rotations. However, our disentangled invariant feature loses the...
Locally Rotation Invariant (LRI) image analysis was shown to be fundamental in many applications and...
Identifying suitable image features is a central challenge in computer vision, ranging from represen...
Most learning methods for 3D data (point clouds, meshes) suffer significant performance drops when t...
Recent investigations on rotation invariance for 3D point clouds have been devoted to devising rotat...
Various recent methods attempt to implement rotation-invariant 3D deep learning by replacing the inp...
Point cloud analysis without pose priors is very challenging in real applications, as the orientatio...
International audienceWe present a novel rotation invariant architecture operating directly on point...
This paper is concerned with a fundamental problem in geometric deep learning that arises in the con...
To form view-invariant representations of objects, neurons in the inferior temporal cortex may assoc...
Establishing correspondences between 3D shapes is a fundamental task in 3D Computer Vision, typicall...
International audienceIn this paper, we propose PCPNET, a deep-learning based approach for estimatin...
Generative models that produce point clouds have emerged as a powerful tool to represent 3D surfaces...
Locally Rotation Invariant (LRI) image analysis was shown to be fundamental in many applications and...
In spite of the recent progresses on classifying 3D point cloud with deep CNNs, large geometric tran...
Most learning methods for 3D data (point clouds, meshes) suffer significant performance drops when t...
Locally Rotation Invariant (LRI) image analysis was shown to be fundamental in many applications and...
Identifying suitable image features is a central challenge in computer vision, ranging from represen...
Most learning methods for 3D data (point clouds, meshes) suffer significant performance drops when t...
Recent investigations on rotation invariance for 3D point clouds have been devoted to devising rotat...
Various recent methods attempt to implement rotation-invariant 3D deep learning by replacing the inp...
Point cloud analysis without pose priors is very challenging in real applications, as the orientatio...
International audienceWe present a novel rotation invariant architecture operating directly on point...
This paper is concerned with a fundamental problem in geometric deep learning that arises in the con...
To form view-invariant representations of objects, neurons in the inferior temporal cortex may assoc...
Establishing correspondences between 3D shapes is a fundamental task in 3D Computer Vision, typicall...
International audienceIn this paper, we propose PCPNET, a deep-learning based approach for estimatin...
Generative models that produce point clouds have emerged as a powerful tool to represent 3D surfaces...
Locally Rotation Invariant (LRI) image analysis was shown to be fundamental in many applications and...
In spite of the recent progresses on classifying 3D point cloud with deep CNNs, large geometric tran...
Most learning methods for 3D data (point clouds, meshes) suffer significant performance drops when t...
Locally Rotation Invariant (LRI) image analysis was shown to be fundamental in many applications and...
Identifying suitable image features is a central challenge in computer vision, ranging from represen...
Most learning methods for 3D data (point clouds, meshes) suffer significant performance drops when t...