Excessive dynamic vary (HDR) pictures methods can precisely seize a scene’s full vary of brightness values — from these of its darkest shadows to its brightest gentle sources. Nevertheless, when the time involves view the ensuing HDR pictures, many shows are solely able to exhibiting a restricted vary of brightness ranges. This discrepancy signifies that HDR pictures are sometimes downgraded to suit inside the bodily limitations of those customary dynamic vary (SDR) shows and the corresponding file codecs that retailer a restricted vary of values.
Nevertheless, an rising share of cellular gadget and laptop shows are HDR-capable, exhibiting a higher vary of brightness ranges with brighter whites and darker blacks. Though a number of frequent HDR file codecs able to encoding this higher vary exist, HDR-only codecs can seem otherwise relying on the show capabilities. To optimally present pictures on any show — irrespective of the dynamic vary — Android 14 launched the brand new Extremely HDR picture format in October 2023. Google Pixel 7 and newer gadgets adopted the format, capturing and saving HDR pictures as Extremely HDR and affording a extra true-to-life rendition as in comparison with SDR codecs, with higher distinction and brighter highlights.
Though the format unlocked HDR picture show, its new metadata additionally elevated the complexity of picture enhancing operations. Till now, in case you utilized a extra complicated edit like Magic Eraser to an Extremely HDR {photograph} utilizing Google Pictures, your new edited picture would save in SDR, shedding its HDR rendition and the related brightness and distinction.
In the present day, we introduce a brand new machine studying (ML) method that permits complicated picture enhancing for HDR pictures, together with these saved as Extremely HDR. On Pixel 8 and newer, our mannequin runs behind the scenes in Google Pictures to make sure that even in case you apply complicated edits to HDR pictures, your new edited pictures stay HDR. Core to our method is predicting the HDR picture metadata lacking after enhancing, utilizing an ML mannequin educated on a big dataset of HDR pictures with full metadata.