Emiliana

Nice, thank you for the updates! I tried using the models you previously posted with the dnn module, but got an error. I assume those already needed a more recent...

With the current OpenCV master branch, I also succeeded in loading the opset11 models (prior to optimization using onnxruntime). For the full landmark model, I get a pure inference time...

For pupil detection, the biggest challenge was finding training data with accurate annotations and variance in pose. Most datasets I looked at had a significant number of annotations that were...

It's good to hear that you could get comparable results. Another thing I thought of, but haven't tried yet, is to train a bigger, slower model which would hopefully give...

That's very interesting! I'm curious to hear about your further results.

Since I posted the previous pytorch weights already, here are the [weights](https://mega.nz/file/nuYHHChJ#PDNOpfmfYC4NNTM7RSiRpiSmPHZshsKn6_1OZ7ofJHA) for the new 56x56 30 point model.

That's an interesting difference. The new model is pretty much the full size model going by layer and channel count, but the resolution of the channels is lower. Maybe that...

One note regarding the `inference=True` code in `model.py`. Some users reported that the landmarks were noisier using this rather than the python landmark decoding function here: https://github.com/emilianavt/OpenSeeFace/blob/e805aa24e35afa3af627bab5f4ede8b9ae4149dd/tracker.py#L718-L747

I merged multiple datasets, partially reannotating them with FAN and older versions of the same model for some features, fixed some eye point annotations in various ways and filtered out...

I can imagine that heatmap based methods lend themselves more to robustness, but I can't give a theoretical reason why. In this case, I think it is a combination of...