Free tool · your photo stays on your device
A selfie is taken from about 30 cm, so close that your nose looks bigger and your face narrower than it is. Add a selfie and slide the camera back, from a 0.5× ultra-wide to a portrait lens, to see your face at 24 mm, 50 mm and 85 mm, then fix your selfie in one tap.
Drop a selfie, paste one, or choose a file
Face straight to the camera, whole face visible. JPG, PNG or WebP.
Runs in your browser. Your photo never leaves your device.
How it is measured
Lens distortion in a face comes from how close the camera is. At 30 cm the tip of your nose is noticeably closer to the camera than your cheeks and ears, so it is drawn bigger and they are drawn smaller. Step back to a metre or two and every part of the face is at nearly the same distance, which is why portrait photographers shoot from further away on an 85 mm lens. This tool maps 478 points on your face with their depth, then redraws your photo as if the camera had been further away, keeping your face the same size in the frame.
How to use it
Sources
The measurement and its reference ranges come from published research. Studies use different methods and populations, so compare your number with the range shown on this page rather than with other tools.
Mita TH, Dermer M, Knight J (1977). Reversed facial images and the mere-exposure hypothesis. Journal of Personality and Social Psychology. doi:10.1037/0022-3514.35.8.597
People preferred their mirror image, while friends preferred their true image: the familiarity effect.
Wang TT, Wessels L, Hussain G, Merten S (2017). Discriminative thresholds in facial asymmetry: a review of the literature. Aesthetic Surgery Journal. PubMed 28200081
How much left–right difference people can notice in a face.
Kartynnik Y, Ablavatski A, Grishchenko I, Grundmann M (2019). Real-time facial surface geometry from monocular video on mobile GPUs. arXiv. arXiv:1907.06724
The face-mesh model that places the 468 surface landmarks this tool measures from.
Ablavatski A, Vakunov A, Grishchenko I, et al. (2020). Real-time pupil tracking from monocular video for digital puppetry. arXiv. arXiv:2006.11341
The iris model that adds 10 eye landmarks (478 in total), used for pupil-based reference lines.
Our own data: how much each reading moves when the same face is photographed again is published on the methodology page. How we choose sources.
Related tools
FAQ
Yes, through distance. A selfie is taken from about 30 cm, close enough that your nose is drawn noticeably bigger and your cheeks and ears smaller than in person. A 2018 study estimated that a selfie at about 30 cm makes the base of the nose look around 30% wider than a photo from 1.5 m.
Not quite. People usually see you from a metre or more, which flattens the nose and widens the face compared with a selfie. Your selfies also tend to be saved un-flipped, the opposite of your mirror.
Portrait photographers usually pick 85 mm to 135 mm, shot from one to two metres away. The face keeps its natural proportions: the nose isn't enlarged and the ears don't disappear.
That is a different effect: at the edges of a wide-angle photo, people are stretched sideways. Stand near the middle of the frame and it goes away.
The ultra-wide camera, about 13 mm on an iPhone, is used very close, which exaggerates the effect: a big nose and forehead, a narrow chin and no ears. That is why 0.5× selfies look funny.
It is a model built from one photo. Depth comes from the face points and the face width is taken as 14 cm, so the amounts are estimates. Ears or hair hidden in the original can't be added back.
No. Everything runs in your browser and the photo never leaves your device.
A controlled scan, every reading against its ideal band, bone vs trainable, a plan, and a 3D model on Face ID iPhones.