Increasing Throughput and Reducing Costs for AI-Based Computer Vision with CV-CUDA

Originally published at:

Real-time cloud-scale applications that involve AI-based computer vision are growing rapidly. The use cases include image understanding, content creation, content moderation, mapping, recommender systems, and video conferencing. However, the compute cost of these workloads is growing too, driven by demand for increased sophistication in the processing. The shift from still images to video is also…

How faster is it compared to equivalent OpenCV operations compiled with GPU support?

1 Like

Sorry for the slow response. We are working on our performance benchmarking and it will be available for a future release. Currently, we have some performance published: CV-CUDA | NVIDIA Developer.

All I see is GPU comparison which is not enough for making a switch from OpenCV. Please update this topic when you get some comparison benchmarks with other frameworks.