Junrou Nishida

I can't say for sure without knowing the details of the benchmark, but since we cannot pass the input data on GPU directly through the Task API for now, there...

> how many ms until we see the change in the pose tracking skeleton. Could you show me in the code exactly from which point to which point the time...

I mean, please indicate the start and end points of the measurement in the code (= line numbers). You don't need to explain it in natural language. For example, from...

It might be correct as a benchmarking of the sample app, but the sample app itself is not implemented with the best latency in mind. Therefore, I don't think it...

It’s a bit cumbersome to explain everything, so I'll just comment on one point: I believe the latency has increased in the process of sending the input image to MediaPipe...

> Here are some "in code" latency measurements: 0.6.2 vs 0.14.4 To reiterate, the method of generating input images is different. In the older implementation, the input images were copied...

In my opinion, the performance of the plugin should be measured by the time from when the input texture is acquired to when the output result is received.

> The sync mode is not working anymore, I could only test the async mode. When the running mode is IMAGE or VIDEO, inference is executed synchronously. While there does...

Since there was no delay when copying the input image [on the CPU](https://github.com/homuler/MediaPipeUnityPlugin/blob/c691e7c85bcffd7e669fe71a08e86dab77bf6b75/Assets/MediaPipeUnity/Samples/Scenes/Face%20Landmark%20Detection/FaceLandmarkerRunner.cs#L101-L110), it seems to be an issue with my implementation. Maybe this is a situation we've encountered [before](https://github.com/homuler/MediaPipeUnityPlugin/blob/c2d594e0639c3d0e9bafb58f9334928db7adc5ee/Assets/MediaPipeUnity/Samples/Common/Scripts/Solution.cs#L77-L78).

> This has nothing to do with latency. If so, I would like you to create a separate issue. Regarding the suggestion that it might be a timestamp problem, I...