Pointpwc-net: Cost volume on point clouds for (self-) supervised scene flow estimation
We propose a novel end-to-end deep scene flow model, called PointPWC-Net, that directly
processes 3D point cloud scenes with large motions in a coarse-to-fine fashion. Flow …
processes 3D point cloud scenes with large motions in a coarse-to-fine fashion. Flow …
Functional maps: a flexible representation of maps between shapes
We present a novel representation of maps between pairs of shapes that allows for efficient
inference and manipulation. Key to our approach is a generalization of the notion of map …
inference and manipulation. Key to our approach is a generalization of the notion of map …
A survey on shape correspondence
We review methods designed to compute correspondences between geometric shapes
represented by triangle meshes, contours or point sets. This survey is motivated in part by …
represented by triangle meshes, contours or point sets. This survey is motivated in part by …
Zoomout: Spectral upsampling for efficient shape correspondence
We present a simple and efficient method for refining maps or correspondences by iterative
upsampling in the spectral domain that can be implemented in a few lines of code. Our main …
upsampling in the spectral domain that can be implemented in a few lines of code. Our main …
Spatially aggregating spectral descriptors for nonrigid 3D shape retrieval: a comparative survey
C Li, A Ben Hamza - Multimedia Systems, 2014 - Springer
This paper presents a comprehensive review and analysis of recent spectral shape
descriptors for nonrigid 3D shape retrieval. More specifically, we compare the latest spectral …
descriptors for nonrigid 3D shape retrieval. More specifically, we compare the latest spectral …
Möbius voting for surface correspondence
Y Lipman, T Funkhouser - ACM Transactions on Graphics (ToG), 2009 - dl.acm.org
The goal of our work is to develop an efficient, automatic algorithm for discovering point
correspondences between surfaces that are approximately and/or partially isometric. Our …
correspondences between surfaces that are approximately and/or partially isometric. Our …
One point isometric matching with the heat kernel
A common operation in many geometry processing algorithms consists of finding
correspondences between pairs of shapes by finding structure‐preserving maps between …
correspondences between pairs of shapes by finding structure‐preserving maps between …
Pointpwc-net: A coarse-to-fine network for supervised and self-supervised scene flow estimation on 3d point clouds
We propose a novel end-to-end deep scene flow model, called PointPWC-Net, on 3D point
clouds in a coarse-to-fine fashion. Flow computed at the coarse level is upsampled and …
clouds in a coarse-to-fine fashion. Flow computed at the coarse level is upsampled and …
Point registration via efficient convex relaxation
Point cloud registration is a fundamental task in computer graphics, and more specifically, in
rigid and non-rigid shape matching. The rigid shape matching problem can be formulated as …
rigid and non-rigid shape matching. The rigid shape matching problem can be formulated as …
On computing mapping of 3d objects: A survey
X Li, SS Iyengar - ACM Computing Surveys (CSUR), 2014 - dl.acm.org
We review the computation of 3D geometric data mapping, which establishes one-to-one
correspondence between or among spatial/spatiotemporal objects. Effective mapping …
correspondence between or among spatial/spatiotemporal objects. Effective mapping …