Connected Cars X
Connected Cars X helps agents to set the smart coverage for aggressive drivers and help regular drivers to save on auto insurance. The solution consists of a Secure Telematics Hardware
The client has a production of souvenirs that represent a translucent cube with a custom 3D sculpture of a human head. The global goal of the customer was to reduce human labor and the time of 3D designers’ work.
One of the most interesting tasks of AI is reconstructing faces or entire heads as 3D models. This task is especially important for creative design agencies that provide branding, advertising, graphic design, and virtual modeling services.
Our client has a production of souvenirs that represent a translucent cube with a custom 3D sculpture of a human head. The agency has 100+ in-house 3D designers to process every image manually. In the past, the flow used to involve designers processing images from clients. The pictures were of poor quality, from social networks or family albums.
Then designers took stock prop of heads, hands, torsos, etc., and sculpted a 3D model that suited the sent image as much as possible. The image was overlaid on top of the created model as a texture. Every image took 15 minutes to process.
The main goal of our customer was to reduce human labor and the time spent by 3D designers.
The customer’s agency had 100+ in-house 3D designers to process every image. In the past, the flow used to involve designers processing images from clients. The pictures could be of poor quality, from social networks or family albums.
Then designers took stock prop of heads, hands, torsos, etc., and sculpted a 3D model that suited the sent image as much as possible. The image was overlaid on top of the created model as a texture. Every image took 15 minutes to process.
We did not take data from designers because they considered the visible side of the head only, thus their 3D models were not symmetrical and had a non-constant number of vertices.
We had to use something other than the state-of-the-art solutions like 2D to 3D neural networks because:
Step 1
Step 2
Principal Component Analysis (PCA) is the most widely used tool in exploratory data analysis and in Machine Learning (ML) for dimensionality reduction. In our case, one PCA component is a set of vectors per vertex. The factor/scalar for one component is the same for all vectors belonging to this component.
Hence, if we found a proper factor for one vertex of the component, we found it for all of the other vertices of the same component.
It helped us to limit the vertices for landmarks only and significantly reduced computational cost.
Step 3
The final 3D reconstruction includes the following:
![]()
It was challenging and interesting to research and solve this 3D head reconstruction project, i.e., find the bugs in facial landmarks detection (heatmap generation) and add more landmarks for the cheek area. Glad we did our best to reduce image processing time to 10 minutes and find the best possible option for this case: Open-sourced Nvidia ICT-FaceKit with blend shapes. It’s a set of 153 PCA components where the first 100 PCA are human-specific variance, like race, gender, age, etc.; and 53 more PCA are emotion-specific variance; with texture mapping, and er-vertex landmark mapping.
![]()
![]()