Weighted voxel: a novel voxel representation for 3D reconstruction
Explore this paper's citation graph
Summary
A new voxel representation, named Weighted Voxel, is defined, which provides more abundant information, facilitating the subsequent learning and generalization steps, and makes full use of the structure information of voxels.
- Type
- article
- Published
- 2018-08-17
- Cited by
- 12
- References
- 17
- Access
- Open access
- OpenAlex
- https://openalex.org/W2892386716
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:52151081
Keywords
Voxel, Computer science, Generalization, Computation, Artificial intelligence
References
- Automatic 3D model acquisition and generation of new images from video sequences
- Long Short-Term Memory
- Ordinal Measures for Image Correspondence
- Simultaneous localization and mapping: part I
- Distinctive Image Features from Scale-Invariant Keypoints
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
- A Review of Geometry Recovery from a Single Image Focusing on Curved Object Reconstruction
- ShapeNet: An Information-Rich 3D Model Repository
- Deep Residual Learning for Image Recognition
- A Point Set Generation Network for 3D Object Reconstruction from a Single Image
- Sequence-to-point learning with neural networks for nonintrusive load monitoring
- 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
- MarrNet: 3D Shape Reconstruction via 2.5D Sketches
- Affine and Projective Structure from Motion
- Deep Learning
- Adam: A Method for Stochastic Optimization
- LSD-SLAM: Large-Scale Direct Monocular SLAM
Cited by
- 3D Reconstruction from A Single Image
- O ESPAÇO-TEMPO COMO PERCEPÇÃO GEOMÉTRICA DA REALIDADE NA FICÇÃO CONTEMPORÂNEA
- 3D reconstruction of coronary arteries using deep networks from synthetic X-ray angiogram data
- Simplified Learning of CAD Features Leveraging a Deep Residual Autoencoder
- Multi-view Pixel2Mesh++: 3D reconstruction via Pixel2Mesh with more images
- Voxel-Based Point Cloud Localization for Smart Spaces Management
- Understanding User Behavior in Volumetric Video Watching: Dataset, Analysis and Prediction
- Development of a Non-Contact Sensor System for Converting 2D Images into 3D Body Data: A Deep Learning Approach to Monitor Obesity and Body Shape in Individuals in Their 20s and 30s
- Multi-view 3D reconstruction based on deep learning: A survey and comparison of methods
- Intelligent Generation of Graphical Game Assets: A Conceptual Framework and Systematic Review of the State of the Art
- Transformer Hypernetworks for Complex Structural Representation
- Improving 3D Human Pose Orientation Recognition Through Weight-Voxel Features And 3D CNNs
Related papers
- An Extant Instance of ‘Q’*
- Doxographi Graeci
- Divided Voxels: An efficient algorithm for interactive cutting of deformable objects
- The Extant Edition of New Anecdotes of the Tang Dynasty Is not a Pseudograph——Challenging Ms Wu Guanwen's Viewpoint
- The extant works
- Surface scan voxel coloring: A surface scan algorithm for scene reconstruction by voxel coloring
- Further results on the fast computation of a class of hydro-mechanical systems
- Why computation need not be traded only for internal representation