Provided by 8i (Maja Krivokuća, Philip A. Chou, and Patrick Savill).
A voxelized point cloud is a set of points constrained to lie on a regular 3D grid, which, without loss of generality, may be assumed to be the integer lattice. The coordinates may be interpreted as the address of a volumetric element, or voxel. A voxel whose address is in the set is said to be occupied; otherwise it is unoccupied. Each occupied voxel may have attributes, such as colour, transparency, normals, curvature, and specularity. A voxelized point cloud captured at one instant of time is a frame. A dynamic voxelized point cloud is represented as a sequence of frames.
The 8iVSLF dataset contains 1 high-resolution, 300-frame sequence, as well as 6 high-resolution single-frame point clouds. For each point cloud in the 8iVSLF dataset, the full body of a human subject was captured by 39 synchronized RGB cameras configured in either 12 or 13 rigs, or clusters (each cluster acting as a logical RGBD camera), at 30 fps. For the contributed video sequence, a 10-second period has been selected from the original captured sequence. The camera rigs were placed around the subject at approximately a couple of metres’ distance. Each cluster of cameras captured RGB and computed depth-from-stereo. The inputs from all the clusters were then fused into a 3D surface.
For each of the contributed point clouds, a single spatial resolution is provided: a cube of 4096 x 4096 x 4096 voxels, known as depth 12 and denoted by vox12 in the name for each frame. For the video sequence, the cube has been scaled so that it is the smallest bounding cube that contains the entire capture area. For this dataset, a voxel represents approximately 1 x 1 x 1 mm of the physical capture space. Since the subject in this dataset takes up less than half the height of the 4096 x 4096 x 4096 cube of voxels, this makes her under 2 m tall, as expected. For the other point clouds in the 8iVSLF dataset, these occupy almost the entire set of 4096 voxels along their longest dimension (i.e., their height), so if we approximate their height as 1.8 m, we can say that a voxel in these datasets is approximately 0.44 mm on a side (i.e., 1.8 m / 4096 voxels ≈ 0.44 mm). In each cube, only voxels that are near the surface of the subject are occupied. For each point cloud in the 8iVSLF dataset, the attributes of an occupied voxel include: the red, green, and blue components of the surface colour as seen by each camera rig, and the x, y, z components of the voxel’s normal vector.
If you publish images of, or report performance results related to, these data, we request that you cite this document as: Maja Krivokuća, Philip A. Chou, and Patrick Savill, “8i Voxelized Surface Light Field (8iVSLF) Dataset,” ISO/IEC JTC1/SC29 WG11 (MPEG) input document m42914, Ljubljana, July 2018.
You can download the full dataset here (24 GB).
|Boxer||Point Cloud 4096 x 4096 x 4096 voxels||Boxer|
|Long Dress||Point Cloud 4096 x 4096 x 4096 voxels||Longdress|
|Loot||Point Cloud 4096 x 4096 x 4096 voxels||Loot|
|Red and |
|Point Cloud 4096 x 4096 x 4096 voxels||RedandBlack|
|Soldier||Point Cloud 4096 x 4096 x 4096 voxels||Soldier|
|Thaidancer||Point Cloud 4096 x 4096 x 4096 voxels||Thaidancer|