https://google.github.io/mediapipe/solutions/models.html#selfie-segmentation

If another try is made, show an error notification instead of failing with an
exception.

This reverts commit 9b6b335c60.

* update virtual background

* remove comments

* remove general model

Prevents downloading wasm module and module each time background is changed

Changed screen capture to non effect. Effects are used to alter the stream, this feature does not need to alter the stream, it just needs access to it

Changed image diff library. Previous library diff’ed the whole image, the new one has en early return threshold

Use ImageCaptureAPI to take the screenshot. Added polyfill for it and polyfill for createImageBitmap

Added analytics

* fix(virtual-background): Fix resize action and prevent mirror behaviour on desktop share as a virtual background.
Co-authored-by: tudordan7 <tudor.pop@decagon.tech>

* fix(wasm-support): WebAssembly browser support.

* fix(wasm-support): WebAssembly browser support.

Co-authored-by: tudordan7 <tudor.pop@decagon.tech>

* audio only screen share implementation

* clean up

* handle stop screen share from chrome window

* update icon

Fixes: https://github.com/jitsi/jitsi-meet/issues/8792

Found via `codespell -q 3 -S ./lang`

When we use a CDN the images come from an origin different than the site so
unless we mark them for CORS the canvas where they are painted will be tainted.

Ref: https://developer.mozilla.org/en-US/docs/Web/HTML/CORS_enabled_image

THis will reuse the previously cached image and obey the base href.

Ref:
https://stackoverflow.com/questions/6241716/is-there-a-difference-between-new-image-and-document-createelementimg

* AudioMixerEffect muted state

* update lib-jitsi-meet

That means all browsers except Safari, for now.

In addition, use the 96p model (instead of the 144p one) on browsers without SIMD support.

Use the Google Meet model and SIMD optimized WASM.

Canvas rendering does not work as expected on Safari - the image stays
still on the first frame. Calling play() on the video tags seems to help.

Do not resize the desktop share to 720p by default when the desktop track resolution is higher than 720p. This is causing bluriness when presenter is turned on.
Remove the 'detail' contentHint setting for the desktop+presenter canvas stream as it forcing chrome to send only 5 fps stream for high resolution desktop tracks.
Move the desktop resizing logic behind a config.js option - videoQuality.resizeDesktopForPresenter.

I don't know how to modify built-in MediaStreamTrack type, so ignore the error.

...so that the text is more readable in the presenter mode. Chrome by
default uses 'detail' for screen sharing. I went with the 'text' here,
because the docs[1] say "may take advantage of encoder tools that
optimize for text rendering." - whether that's good specifically for
the presenter mode I don't know. It looked good for me when tested
on Chrome.

https://www.w3.org/TR/mst-content-hint/

* feat(blur): terminate blur web worker when disabled

* Update JitsiStreamPresenterEffect.js
Create/terminate the Web Worker on effect start/stop so that we don't leak them.

On electron 7 drawing on hidden canvas will trigger a memory leak.
Not appending the canvas for the DOM seems to solve the problem.