`suppress_implausible_poses` cannot be used with external bbox detector

[Timm Linder]

Hi @isarandi! I just noticed that when using an external 2D bbox detector, i.e. directly calling the tf.function estimate_poses_batched() on a saved model as opposed to detect_poses_batched(), it is not possible to enable plausability filtering of poses.

The reason is that, whilst the private Pose3dEstimator._estimate_poses_batched() method does expose the parameter suppress_implausible_poses, the public tf.function estimate_poses_batched() does not expose the parameter and has it hard-coded internally to False.

I assume this cannot be easily fixed without re-training and re-exporting the saved models, but I just wanted to document it here for the sake of completeness.

[István Sárándi]

Hi Timm,

True, good catch! My reasoning here was that in this case the user decided the bounding boxes already, so it's more logical to return the results for exactly those, in the same order. Otherwise the API would also need to change, to return somehow which boxes got a result and which were discarded. It could be done, but I tried to keep this simpler.

[Stefano Berti]

Hi @isarandi , I saw that in filter_poses you used a bone_dataset.joint_info to filter implausible poses. Where can I find it?