RealityCapture Tarasque 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 3.0+ capabilities and 1GB VRAM
- CUDA Toolkit 10.2, minimal driver version 441.22.
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 a 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 3.0+ 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.
You can easily register an unlimited number of images/laser-scans on a single machine. However, it requires a specific workflow using components. In such a case, 16GB should be enough for thousands of high (36-80 MPX) resolution images. You can find more information about components workflow in the application Help, section Using components.
To align an unordered set of images into one component you will need a certain amount of RAM. The consumption depends on a count of images (irrespective of their size) and a count of features per image. If you restrict the count of features per image from default 40K to 20K, you will double the count of images that 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.
Here you can find a performance comparison of a specific HW equipment during processing in RealityCapture provided by Puget Systems: