Here at Puget Systems, we have put together a benchmark utility for RealityCapture which measures system performance for photogrammetry by running two small projects – a model and a map – and tracking the time each step takes to process. This benchmark is freely available to download, though running it requires a valid installation of RealityCapture.
Pix4D 4.3: Intel Core i9 9990XE Performance
Pix4D is an advanced photogrammetry application, suited to a wide range of uses, with a focus on handling images captured by drone cameras. Processing of those images into point clouds and 3D meshes/textures is time-consuming, heavily using a computer’s CPU and GPU. Both core count and clock speed play a role in Pix4D performance, so when Intel released their new Core i9 9990XE with very high clock speeds and a respectable number of cores (14, plus Hyperthreading) this seemed like a good application to test on it.
Testing Dynamic Local Mode on AMD Threadripper 2970WX – Photogrammetry
Dynamic Local Mode is a new feature on AMD’s biggest Threadripper processors. These CPUs have cores grouped internally, some with direct access to system memory and some which have to communicate through those other cores to access data in memory. DLM prioritizes running code on the cores which have a direct line to the memory, helping to improve performance in situations where not all of the cores are in use. How does that translate to real-world workloads, though? Let’s take a look at two photogrammetry applications and see how the 24-core 2970WX behaves with this feature on and off.
Pix4D 4.3 GPU Comparison: GeForce RTX 2070, 2080, and 2080 Ti
Pix4D is an advanced photogrammetry application, suited to a wide range of uses, with a focus on handling images captured by drone cameras. Processing of those images into point clouds and 3D meshes / textures is time-consuming, heavily using a computer’s CPU and GPU. A new version, 4.3, was released recently – so we have tested multiple projects across the new GeForce RTX series of video cards, as well as the previous generation, to see which graphics card performs the best.
Pix4D 4.3 CPU Comparison: Intel 9th Gen Core & X-series vs AMD Ryzen & Threadripper
Pix4D is an advanced photogrammetry application, suited to wide range of uses, with a focus on handling images captured by drone cameras. Processing of those images into point clouds and 3D meshes / textures is time consuming, heavily using a computer’s CPU and GPU. A new version, 4.3, was released recently – so we have tested multiple projects across a wide range of CPUs to see what hardware performs the best.
Pix4D 4.3 Multi-GPU Scaling and NVLink
Pix4D is an advanced photogrammetry application, suited to a wide range of uses, with a focus on handling images captured by drone cameras. Processing of those images into point clouds and 3D meshes/textures is time-consuming, heavily using a computer’s CPU and GPU. In this article, we are looking at whether multiple GPUs improve Pix4D performance and if NVLink has any impact.
Pix4D 4.3 vs 4.2 Performance Analysis
Pix4D is an advanced photogrammetry application, suited to wide range of uses, with a focus on handling images captured by drone cameras. Processing of those images into point clouds and 3D meshes / textures is time consuming, heavily using a computer’s CPU and GPU. A new version, 4.3, was released recently – so we are taking a look at performance of the previous version versus this one to see if there have been any improvements.
Pix4D GPU Comparison: GeForce, Titan, and Quadro
Pix4D is an advanced photogrammetry application, suited to wide range of uses, with a focus on handling images captured by drone cameras. Processing of those images into point clouds and 3D meshes / textures utilizes the video card (GPU) in a workstation, but how much impact do different cards make on overall performance?
Pix4D CPU Comparison: Coffee Lake vs Skylake X vs Threadripper
Pix4D is an advanced photogrammetry application, suited to wide range of uses, with a focus on handling images captured by drone cameras. Processing of those images into point clouds and 3D meshes / textures is time consuming, so we have tested multiple projects across a wide range of CPUs to see what hardware performs the best.