Kinect Deform: Enhanced 3D Reconstruction of Non-rigidly Deforming Objects
Explore this paper's citation graph
Summary
This work proposes KinectDeform, an algorithm which combines a fast non-rigid scene tracking algorithm based on octree data representation and hierarchical voxel associations with a recursive data filtering mechanism and shows improved results in terms of smoothness and feature preserving 3D reconstructions with reduced noise.
- Type
- article
- Published
- 2014-12-08
- Cited by
- 9
- References
- 37
- Access
- Open access
- OpenAlex
- https://openalex.org/W113366354
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:8537795
Keywords
Octree, Computer science, Computer vision, Artificial intelligence, Voxel
References
- Kintinuous: Spatially Extended KinectFusion
- Robust single-view geometry and motion reconstruction
- KinectFusion: Real-time dense surface mapping and tracking
- A volumetric method for building complex models from range images
- Lightweight binocular facial performance capture under uncontrolled lighting
- Moving Volume KinectFusion
- OmniKinect: real-time dense volumetric data acquisition and applications
- Toward a real-time tracking of dense point-sampled geometry
- Folding and crumpling adaptive sheets
- Real-Time 3D Reconstruction in Dynamic Scenes Using Point-Based Fusion
- Real-time 3D reconstruction at scale using voxel hashing
- Real-time non-rigid reconstruction using an RGB-D camera
- Adaptive anisotropic remeshing for cloth simulation
- Multi-view Scene Flow Estimation: A View Centered Variational Approach
- Global Correspondence Optimization for Non‐Rigid Registration of Depth Scans
- Bilateral filtering for gray and color images
- KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera
- LidarBoost: Depth superresolution for ToF 3D shape scanning
- Templateless Quasi-rigid Shape Modeling with Implicit Loop-Closure
- Interactive ray tracing for isosurface rendering
Cited by
- Super-Resolution Approaches For Depth Video Enhancement
- Fast capture of textured full-body avatar with RGB-D cameras
- Real-Time Enhancement of Dynamic Depth Videos with Non-Rigid Deformations
- Optimized KinectFusion Algorithm for 3D Scanning Applications
- Full 3D Reconstruction of Non-Rigidly Deforming Objects
- Improved real-time rendering for mixed reality
- Achieving Flexible 3D Reconstruction Volumes for RGB-D and RGB Camera Based Approaches
- View-Independent Enhanced 3D Reconstruction of Non-rigidly Deforming Objects
- An Optimized Method for 3D Body Scanning Applications Based on KinectFusion
Related papers
- G-ML-Octree: An Update-Efficient Index Structure for Simulating 3D Moving Objects Across GPUs
- Using Extended Octree Algorithm to Model Virtual Sculpting Geometry
- An Improved Three-Dimensional Target Octonion Representation
- Study of virtual octree model for volume data
- Using pseudo voxel octree to accelerate collision between cutting tool and deformable objects modeled as linked voxels
- Fast Large Scale Voxelization Using Projection Volume and Octree
- Efficient linear octree generation from voxels