Learning multiview 3d point cloud registration
We present a novel, end-to-end learnable, multiview 3D point cloud registration algorithm.
Registration of multiple scans typically follows a two-stage pipeline: the initial pairwise …
Registration of multiple scans typically follows a two-stage pipeline: the initial pairwise …
Weakly supervised learning of rigid 3D scene flow
We propose a data-driven scene flow estimation algorithm exploiting the observation that
many 3D scenes can be explained by a collection of agents moving as rigid bodies. At the …
many 3D scenes can be explained by a collection of agents moving as rigid bodies. At the …
Nrdf: Neural riemannian distance fields for learning articulated pose priors
Faithfully modeling the space of articulations is a crucial task that allows recovery and
generation of realistic poses and remains a notorious challenge. To this end we introduce …
generation of realistic poses and remains a notorious challenge. To this end we introduce …
3D local features for direct pairwise registration
We present a novel, data driven approach for solving the problem of registration of two point
cloud scans. Our approach is direct in the sense that a single pair of corresponding local …
cloud scans. Our approach is direct in the sense that a single pair of corresponding local …
Explaining the ambiguity of object detection and 6d pose from visual data
Abstract 3D object detection and pose estimation from a single image are two inherently
ambiguous problems. Oftentimes, objects appear similar from different viewpoints due to …
ambiguous problems. Oftentimes, objects appear similar from different viewpoints due to …
Quaternion equivariant capsule networks for 3d point clouds
We present a 3D capsule module for processing point clouds that is equivariant to 3D
rotations and translations, as well as invariant to permutations of the input points. The …
rotations and translations, as well as invariant to permutations of the input points. The …
Learning to communicate and correct pose errors
Learned communication makes multi-agent systems more effective by aggregating
distributed information. However, it also exposes individual agents to the threat of erroneous …
distributed information. However, it also exposes individual agents to the threat of erroneous …
Multibodysync: Multi-body segmentation and motion estimation via 3d scan synchronization
We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation
and rigid registration framework for multiple input 3D point clouds. The two non-trivial …
and rigid registration framework for multiple input 3D point clouds. The two non-trivial …
Multiway non-rigid point cloud registration via learned functional map synchronization
We present SyNoRiM, a novel way to jointly register multiple non-rigid shapes by
synchronizing the maps that relate learned functions defined on the point clouds. Even …
synchronizing the maps that relate learned functions defined on the point clouds. Even …
Deep bingham networks: Dealing with uncertainty and ambiguity in pose estimation
In this work, we introduce Deep Bingham Networks (DBN), a generic framework that can
naturally handle pose-related uncertainties and ambiguities arising in almost all real life …
naturally handle pose-related uncertainties and ambiguities arising in almost all real life …