A morphable model for the synthesis of 3D faces
Proceedings of the 26th annual conference on Computer graphics and interactive techniques
Multi-scale EM-ICP: A Fast and Robust Approach for Surface Registration
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
The space of human body shapes: reconstruction and parameterization from range scans
ACM SIGGRAPH 2003 Papers
Deformation transfer for triangle meshes
ACM SIGGRAPH 2004 Papers
SCAPE: shape completion and animation of people
ACM SIGGRAPH 2005 Papers
Proceedings of the 2006 ACM SIGGRAPH/Eurographics symposium on Computer animation
Embedded deformation for shape manipulation
ACM SIGGRAPH 2007 papers
As-rigid-as-possible surface modeling
SGP '07 Proceedings of the fifth Eurographics symposium on Geometry processing
A Data-driven Approach to Human-body Cloning Using a Segmented Body Database
PG '07 Proceedings of the 15th Pacific Conference on Computer Graphics and Applications
Robust single-view geometry and motion reconstruction
ACM SIGGRAPH Asia 2009 papers
A 3D Face Model for Pose and Illumination Invariant Face Recognition
AVSS '09 Proceedings of the 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance
Global correspondence optimization for non-rigid registration of depth scans
SGP '08 Proceedings of the Symposium on Geometry Processing
Face models from noisy 3D cameras
ACM SIGGRAPH ASIA 2010 Sketches
Detailed human shape and pose from images
Detailed human shape and pose from images
Landmark-free posture invariant human shape correspondence
The Visual Computer: International Journal of Computer Graphics
| Hi-index | 0.00 |
Three-dimensional (3D) shape models are powerful because they enable the inference of object shape from incomplete, noisy, or ambiguous 2D or 3D data. For example, realistic parameterized 3D human body models have been used to infer the shape and pose of people from images. To train such models, a corpus of 3D body scans is typically brought into registration by aligning a common 3D human-shaped template to each scan. This is an ill-posed problem that typically involves solving an optimization problem with regularization terms that penalize implausible deformations of the template. When aligning a corpus, however, we can do better than generic regularization. If we have a model of how the template can deform then alignments can be regularized by this model. Constructing a model of deformations, however, requires having a corpus that is already registered. We address this chicken-and-egg problem by approaching modeling and registration together. By minimizing a single objective function, we reliably obtain high quality registration of noisy, incomplete, laser scans, while simultaneously learning a highly realistic articulated body model. The model greatly improves robustness to noise and missing data. Since the model explains a corpus of body scans, it captures how body shape varies across people and poses.