Erase annoying tourists from your holiday photos and videos! iPhone app makes people and objects disappear with the touch of a button

  • App can erase people and cars from static images such as that of a landscape 
  • Spectre's makers say the software uses AI to stabilise long exposures
  • Moving parts during the long exposure are removed at the touch of a button 
  • It could mean the end of near-perfect holiday snaps ruined by hoards of tourists

A new camera app for iPhone lets you erase annoying tourists, cars or other objects that block your perfect shot.

Spectre uses AI technology to stabilise long-exposure photos, focusing on the stationary part of a frame erasing moving parts, including people and objects. 

Near-perfect holiday snaps of beautiful views cluttered with people appear as if you have beaten the crowds and arrived to enjoy scenic vistas all to yourself.  

Scroll down for video 

A  new camera app called Spectre for iOS that lets iPhone users 'erase' traces of people and cars from scenic shots. The camera app uses AI technology to stabilise long-exposures, and focuses on the stationary part of a shot, allowing users to erase the moving parts
Slide me

A new camera app for iPhone lets you erase annoying tourists, cars or other objects that block your perfect shot. Spectre uses AI technology to stabilise long-exposure photos, focusing on the stationary part of a frame erasing moving parts, including people and objects  

Halide, the company behind the software, says its new app can generate such 'magic' photos by using AI technology in several ways.  

The software can recognise the type of scenery the user is trying to capture, and enhance the image accordingly.

For example, it can blend waves in a picture of the beach, to create atmospheric effects that provide a sense of motion. 

'[Spectre's] intelligent shutter takes hundreds of photos during the exposure time and merges the result,' said Sebastiaan de With, the app's designer.

'That means you don't just get a final still image, but also a video of the entire exposure as it happened.'

Spectre's ability to stabilise shots for a long exposure time, where the shutter stays open for up to nine seconds.

The company claims its AI 'image stabilisation' technology means it can reproduce clear long exposure images without the need for professional equipment like tripods.  

Spectre uses AI technology to stabilise long-exposures that usually require extra stabilisation. The app says the AI can also recognise the type of scenery being captured  and blend the hundreds of images taken during a nine second exposure to create an enhanced finish

Spectre uses AI technology to stabilise long-exposures that usually require extra stabilisation. The app says the AI can also recognise the type of scenery being captured and blend the hundreds of images taken during a nine second exposure to create an enhanced finish

Special effects already let Hollywood filmmakers remove unwanted objects and people from their final shots are commonly used.

Adobe has also unveiled a peak of its Cloak project, which will let members of the public automatically edit their own footage in this way, which would take professionals hours to complete.

Users of the tool, which is currently under development, can select any item for deletion and smart software fills in the gap.

The company has not yet given any indication of when Cloak will be released.

Spectre is available in the US iOS store for $2.99 (£2.28) but not yet available in the UK store. 

Long exposure times that create professional looking images often need to be stabilised using equipment like tripods. Spectre claims capturing of images in the usual hand held way on phones was sufficient to produce a clear picture due to its AI 'image stabilisation' technology.

Long exposure times that create professional looking images often need to be stabilised using equipment like tripods. Spectre claims capturing of images in the usual hand held way on phones was sufficient to produce a clear picture due to its AI 'image stabilisation' technology.

HOW ARTIFICIAL INTELLIGENCES LEARN USING NEURAL NETWORKS

AI systems rely on artificial neural networks (ANNs), which try to simulate the way the brain works in order to learn.

ANNs can be trained to recognise patterns in information - including speech, text data, or visual images - and are the basis for a large number of the developments in AI over recent years.

Conventional AI uses input to 'teach' an algorithm about a particular subject by feeding it massive amounts of information.   

AI systems rely on artificial neural networks (ANNs), which try to simulate the way the brain works in order to learn. ANNs can be trained to recognise patterns in information - including speech, text data, or visual images

AI systems rely on artificial neural networks (ANNs), which try to simulate the way the brain works in order to learn. ANNs can be trained to recognise patterns in information - including speech, text data, or visual images

Practical applications include Google's language translation services, Facebook's facial recognition software and Snapchat's image altering live filters.

The process of inputting this data can be extremely time consuming, and is limited to one type of knowledge. 

A new breed of ANNs called Adversarial Neural Networks pits the wits of two AI bots against each other, which allows them to learn from each other. 

This approach is designed to speed up the process of learning, as well as refining the output created by AI systems. 

Advertisement

The comments below have not been moderated.

The views expressed in the contents above are those of our users and do not necessarily reflect the views of MailOnline.

We are no longer accepting comments on this article.