How the Strategic and Technical Collaboration Between MindInventory and Passio.AI Transformed into a Revolutionary AI Ally

Passio.AI

The Brief

  • Passio is the cutting-edge AI platform that enables organizations to incorporate vertical-specific computer vision functionalities into their apps, fostering the development of AI-driven sales and UX experiences. Passio AI SDKs and Modules are equipped with reference applications and sample code, facilitating seamless integration for businesses to create their own white-label products.
  • With the world's largest visual database, Passio stands as the backbone for numerous global-leading AI-based applications, including MyFitnessPal, Jazeera Paints, Elevance Health, Simple Life, and more.
  • This case study delves into the intricate details of our contributions toward crafting advanced AI, AR/VR, and Computer Vision-based SDK modules and applications. These innovations empower businesses to ascend towards intelligent leadership, transforming their operations and customer experiences.
passio
our journey

The Challenge

  • The SDK developed by our customer captures data; however, they did not have the in-house capability of building an application around it that can showcase the functionalities skillfully. They also needed an extended team of technical talents onboard to expand their SDK use cases and dedicatedly help them make the global-leading AI-powered app-based business entity - someone they can ensure collaborative, long-term, technical business relationships.
  • Creating a real-time experience for people is quite a massive task, but Passio found us capable of performing these tasks.
kitchen aig

The Solution

  • Our approach to resolving the identified issues involved the development and implementation of a tailored solution that seamlessly integrated with the existing framework.
  • We didn't just work with the Passio.AI team as their service provider but more like their extended remote team that's been proactively participating in their brainstorming sessions for extending SDK capabilities, experimenting and figuring out more use cases, and helping their clients create and integrate Passio.AI functionalities into their apps to become AI-powered ones. Our contribution to the Passio.AI products include:

Paints.AI

Our team worked on five approaches for mapping walls: Legacy swatch allowing to fill colors in the selected squares, Floor Plan allowing to point out corners to create AR walls for color selection (which uses OpenGL Shading Language (GLSL)), Room Plan (available in iOS only) allowing scan and generate 3D geometry model that recognises objects and walls to apply paints on, Color Range identifies wall colors and allows to change particular color parts (in iOS app it uses LiDAR scanner to measure area size), and many other features.

Nutrition AI

Understanding the need of nutritionists and doctors to receive daily meal updates from customers, and even help users to track their meal and nutrition consumptions, we helped the Passio.AI team with their Nutrition AI SDK modifications and provided cross-platform application development using React Native and Flutter to make it compatible with various platforms and devices. We also suggested creating a feature to generate a doctor's report to share it in PDF form. Any business can subscribe for this SDK and offer users AI-driven fitness journeys.

Segment Anything Model

We also assisted in the modification of the Segment Anything Model (SAM), an AI model that allows users to select any already clicked image from the gallery and produce high-quality object masks to virtually try on things, such as Paints on walls. It has been trained on a dataset of 11 million images and 1.1 billion masks, has strong zero-shot performance in segmentation tasks, and offers great accuracy.

Synthetic Data Generation

Initially, when testing the application for applying color and texture filters on the wall, we encountered various issues, such as colors being applied to objects placed near the wall. To rectify this, we proposed training the computer vision model to distinguish between objects and walls. Our suggestion involved generating image-based synthetic data, a process in which our team of 2D/3D artists played a pivotal role.

Anomaly Detection

Computer vision techniques are employed to analyze the live video footage of walls and identify patterns that deviate from the expected appearance of a well-maintained surface. Considering that there could be damage in the wall, the application will help you detect any anomalies in the wall (in the form of breakages, cracks, and holes), detect the depth of the damage, and suggest the amount of material required to make repairs. Python and Google AI were used to train the models.

AR/VR Kit Support

We modified the AR models provided by the Passio team for different business applications. Our team developed the AR/VR functionality for the Android platform, especially for the Paints AI and Remodel AI modules, that lets users take a virtual tour of the property and reimagine its interior with different colors and textures. It plays a key role in room mapping, as the user needs to jot the corners of a room, and the application generates a 3D model that visualizes the entire room, letting users take a virtual tour of it, and even apply filters and check different colors and texture on the wall for better interior planning.

The Impact

  • We helped them with the output they were expecting within the specific timeline, and we managed to live up to their expectations. Our proficient team of engineers worked on their requirements and provided them with real-time solutions, along with dedicated ongoing support and maintenance. Our engagement with Passio.AI has lasted over several years and continues to grow as we play an active role in creating tangible products that disrupt industries.
95%

Accuracy for Paint.AI

97%

Accuracy for Nutrition AI

27%

Reduction in Dietary Mistakes

home ai
Construction-AI
nutrition ai
×

Can't find what you're looking for?

We'd love to hear about your unique requirements! How about we hop on a quick call?

attach_file

Attach a file

Please upload a file with one of the following extensions: .pdf, .docx, .odt, .ods, .ppt/x, .xls/x, .rtf, .txt
MAY BE LATER
exit init