Drop us a line
If you are interested in the development of a custom solution — send us the message and we'll schedule a talk about it.
Azati Software
Image Modeling Application
Implementing our startup idea – the application that allows us to immediately change wallpapers on the photo taken from a smartphone.
CUSTOMER
The purchase of new property or real estate, interior change and all design stuff is quite an expensive and time-consuming process. Moreover, if you aren’t satisfied with the result you will spend much more resources. In this regard, Azati helps our customer, engaged in an interior design and decoration agency, to create one interesting application.
Objective
In our increasingly digitized world, where everything from our phones to our thermostats is “smart,” it should come as no surprise that virtual reality (VR) and augmented reality (AR) are starting to play a role in the design industry.
It’s a logical relationship: designers have always imagined new or re-imagined existing spaces, created a drawing via analog means or digital ones, and presented that visualization to their clients.
The Azati team created an application to change the room wallpaper interior by one click via smartphone.
Challenge
A request for a visualization of a room covered with new wallpapers appears very frequently. Currently, all the design agencies can do to satisfy this need is to present drawings and models of interior designs created with 3D rendering applications or other software tools. The main drawback of this approach is that it takes several days to prepare the final image.
Another option is to use applications, which enable to change only the confined set of prepared photos of the interiors. Both variants fail to deliver the level of performance the clients want.
The perfect solution implies utilizing instant modeling, which represented the main challenge due to its technical complexity.
Solution
Azati development team created a fast and easy-to-use application that works both on mobile phone and web browsers.
Artificial Intelligence methods analyze the photo in several stages to perform semantic segmentation of the room – the application recognizes the ceiling, floor, furnishings and decorations. Our algorithms distinguish even the small elements like pillars, wall niches, arches etc. To make the chosen wallpapers look natural on the result image, the algorithms also consider lightning, define depth and surfaces of walls.
There are many wallcovering options available – different colours, textures, and geometric patterns can be applied.
At the last step, the application replaces the existing wallcovering with a new choice, thus building a plausible model of a new room.
Technologies
SCREENSHOTS
Featured case studies:
JavaScript, Ruby
HR Planning SoftwareThe customer asked Azati to audit the existing solution in terms of general performance to create a roadmap of future improvements. Our team also increased application performance and delivered several new features.
Python
Stock Market Trend Discovery with Machine LearningAt Azati Labs, our engineers developed an AI-powered prototype of a tool that can spot a stock market trend. Online trading applications may use this information to calculate the actual stock market price change.
Python
Semantic Search Engine for Bioinformatics CompanyAzati designed and developed a semantic search engine powered by machine learning. It extracts the actual meaning from the search query and looks for the most relevant results across huge scientific datasets.
Java, JavaScript
E-health Web Portal for International Software IntegratorAzati helped a well-known software integrator to eliminate legacy code, rebuild a complex web application, and fix the majority of mission-critical bugs.
JavaScript, Ruby
Custom Platform for Logistics and Goods TransportationAzati helped a European startup to create a custom logistics platform. It helps shippers to track goods in a real-time, as well as guarantees that the buyer will receive the product in a perfect condition.
