Approved for Public Release, Distribution Unlimited Real-time Rendering and Dynamic Updating of 3-d Volumetric Data

By Andrew Miller, Vishal Jain, J. Mundy

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Andreas Geiger
2. Michael J. Black
3. Ali O. Ulusoy
4. Gernot Riegler
5. Luc Van Gool
6. Jitendra Malik
7. Ming-Hsuan Yang
8. Yiyi Liao

Citations in the corpus

• OctNet: Learning Deep 3D Representations at High Resolutions (2016, methodology): “In contrast to [31], we associate a data container (for storing features vectors) with all leaf nodes of each shallow tree.”
• OctNetFusion: Learning Depth Fusion from Data (2017, methodology): “[36] utilize this observation and define a CNN on the grid-octree data structure of [29].”
• Towards Probabilistic Volumetric Reconstruction Using Ray Potentials (2015, methodology): “In particular, we use shallow octrees amenable to GPU processing proposed by Miller et al. [21].”
• Semantic Multi-view Stereo: Jointly Estimating Objects and Voxels (2017, methodology): “Runtime: Our implementation uses grid-octree data structures [24] and GPGPU parallelization for message passing.”