RealityCapture V1.0 BETA requires:
- 64bit machine with at least 8GB of RAM
- 64bit Microsoft Windows version 7 / 8 / 8.1 / 10 or Windows Server version 2008+
- NVIDIA graphics card with CUDA 2.0+ capabilities and 1GB RAM.
We recommend using a machine with at least 4 CPU cores, 16GB of RAM and 1024 CUDA cores. If you do not have the NVIDIA card, you will be still able to run the application and register images, you will not be able to create textured mesh.
The CPU is required to support SSE4.2 (Streaming SIMD Extensions 4.2) or higher.
How to find out whether you have CUDA 2.0+ update the drivers and check here: https://developer.nvidia.com/cuda-gpus
For Microsoft Windows N you will need to install Media Feature Pack for Windows. Click the following link to install it: http://www.microsoft.com/en-us/download/details.aspx?id=16546. If you are using Windows Server, then you need to install Media Foundation features.
The RealityCapture application uses state-of-the-art out-of-core algorithms for almost every task. Therefore, you do not need to worry about computer memory. However, to achieve the great performance which RealityCapture image registration has, it consumes a little bit more memory.
The consumption depends on a count of images (irrespective of their size) and a count of (preselector) features per image. For the default settings, you can expect the following memory boundaries:
- 2,000 images (scans) / 40K features per image - 16GB RAM
- 4,000 images - 32GB RAM
- 8,000 images - 64GB RAM
- 16,000 images - 128GB RAM
The memory consumption scales linearly. These boundaries hold when you are feeding the application with all images at once. You can significantly reduce the memory consumption by using components. Please refer to appropriate forum topics for reference. Also, if you restrict the count of features per image to 20K, you will double the count of images which can use the same amount of RAM.
Meshing, coloring and texturing are completely out-of-core. Hence you do not need to worry about the computer RAM at all. This means that once you have even one million images or scans registered together, you can create a mesh and a texture on a machine with e.g. 16GB of RAM without any performance loss.
Each RC license is limited to 32 CPU cores and 3 GPU cards. If you want to use higher configuration, you need to purchase more licenses equivalently.