Altis is the world’s first AI personal trainer.
Altis sees you, understands you, and personally instructs you in real-time from a sleek soundbar-size console that connects to any screen on your home. The future of fitness is finally here.

Client
Altis is the world's first AI personal trainer
Industry
Digital Consumer Product/Service

THE OPPORTUNITY

“As an AI-first company, Dianthus seeks out fellow deep learning researchers who can offer unique experience and perspective in applying and implementing cutting-edge solutions in AI and ML to partner with our in-house AI teams.”– Altis Executive

“Custom AI development for new and innovative products can be a risky endeavor without a disciplined approach to experimentation, broad domain knowledge and experience implementing the latest research and architectures. Neu.ro’s combination of PhD-level AI expertise and an extremely robust foundation in MLOps gave us the confidence that our project would be handled both innovatively and responsibly.”– Altis Executive

“Neu.ro went above and beyond in terms of identifying and implementing cutting edge deep learning techniques to create a genuinely innovative solution. We look forward to continuing to advance the state of the art in the area of AI-generated visual marketing with them.”– Altis Executive

In the new post-pandemic, work from anywhere world, home fitness is booming. Peloton is a famous growth leader, with paid digital subscribers increasing 176% y/y in their last quarter. Apple recently announced a subscription fitness service providing guided classes via their Apple TV product and incorporating input from their Apple Watch sensors.

Altis aims to go one step further by incorporating AI vision technology using multiple camera sensors to accurately track and analyze movement and provide guided fitness instruction and form coaching for fitness and sports applications.

Challenge
Altis is an exciting consumer AI startup with the ambitious goal of offering customized personalized fitness training in the comfort of your home.

Beyond just pose estimation and tracking, the proposed AI system needed to be able to identify precise exercises, identify errors in those exercises vs. ideal form, support multiple cameras and work in real time.

The Challenge

The specifics of Altis’ proposed use cases meant they needed a system that could accurately detect a large number of exercises, including exercises using popular gym equipment, weights, machines, etc.

Solution
Real-time pose detection for individual fitness instruction and coaching

The Altis console provides personalized workouts and interactive coaching using advanced AI and computer vision to help you reach your fitness goals, understand how your body is moving during exercise and improve form and movement performance.
Results
A unique data pipeline and extensive research was required to identify the necessary models and enable them to be trained in an unsupervised way. The resulting model achieved a median error of less than 3cm per keypoint, allowed for multiple sensors to be used and achieved suitable speed requirements.

The Solution

Neu.ro researchers developed a custom data pipeline that employs volumetric triangulation from one or more RGB cameras, combines 2D backbone data into volumetric aggregation of intermediate 2D feature maps followed by refinement via 3D convolutions resulting in a 3D heatmap and pose model.

The system runs in real-time on Nvidia 3090 hardware and runs at 75 FPS while pose tracking, but has a startup mode of 30 FPS that runs until a person is detected.

This volumetric model is able to estimate 3D human pose using any number of cameras, even using only 1 camera. In single-view setup we get results comparable with current state of the art, while multiple sensors result in faster processing and fewer errors from potential occlusions.