I'm trying to create a sky mask on pictures taken from my iPhone. I've seen in the documentation that CoreImage support semantic segmentation for Sky among other type for person (skin, hair etc...) For now, I didn't found the proper workflow to use it. First, I watched https://developer.apple.com/videos/play/wwdc2019/225/ I understood that images must be captured with the segmentation with this kind of code: photoSettings.enabledSemanticSegmentationMatteTypes = self.photoOutput.availableSemanticSegmentationMatteTypes photoSettings.embedsSemanticSegmentationMattesInPhoto = true I capture the image on my iPhone, save it as HEIC format then later, I try to load the matte like that : let skyMatte = CIImage(contentsOf: imageURL, options: [.auxiliarySemanticSegmentationSkyMatte: true]) Unfortunately, self.photoOutput.availableSemanticSegmentationMatteTypes always give me a list of types for person only and never a types Sky. Anyway, the AVSemanticSegmentationMatte.MatteType is just [Hair, Skin, Teeth, Glasses] ... No Sky !!! So, How am I supposed to use semanticSegmentationSkyMatteImage ?!? Is there any simple workaround ?

I'm currently testing Photogrametry by capturing photos with sample project https://developer.apple.com/documentation/realitykit/taking_pictures_for_3d_object_capture Then use them on my laptop with https://developer.apple.com/documentation/realitykit/creating_a_photogrammetry_command-line_app It worked perfectly until the latest updates of Sonoma BETA. It started by warning logs in the console saying I lacked depthMap in my samples and now it just refuse to create samples from my HEIC files. I tried to create HEIC files with and without Depth data to check if it's a bad format of these depth data but it seems it's just the HEIC format itself that is not accepted anymore. I've also just imported HEIC files captured with the standard iOS app and transferred what Photo app and they doesn't work either so it's not an issue of poorly formatted files. If I convert the files in PNG, it works again but of course, as announced during WWDC 2023, I expect to get the photogrammetry pipeline leverage the LIDAR data ! I check every BETA update waiting for an improvement. I can see the photogrammetry logs are never the same so I guess the apple teams are working on it. Of course, the object capture model from Reality Composer pro, also doesn't accept HEIC files anymore. If there are some workarounds, please advise !