A neural network that enhances videos with animation and vibrant colors

Analysis and processing of video streams

ESSA logo




Advertising agency APM is a partner of AB InBev Efes, a producer of beer and non - alcoholic beverages in Russia and Ukraine.


ESSA ran an ad in which a person and their background were painted in different colors.

A task

Create a service where VKontakte and Telegram users will be able to create similar videos.
APM logo

What we came up with


A neural network that creates different video effects:

«Neon boom»
with the appearance of contrasting countrours the user's body, eyes, mouth, and clothes
with a wave filling the contour of a person
«Bright party»
with solid colors fill in the different body parts and clothes
Волна, заполняющая контур человека
Сплошная цветовая заливка частей тела, глаз, губ, одежды
Появление контрастных контуров тела, глаз и рта, одежды

What the neural network is capable of

Distinguish a person from furniture and background
Segment objects and paint them in different colors
Designate eyes, hair, drawing on clothes with different colors

How it works

User reads the QR code on the ESSA beer bottle with his phone
The ESSA "VKontakte" service page opens on the phone
Чат-бот Essa
*uploads video*
*selects video effect*
Hey! This is Essa's chatbot and I can animate any dance video of yours! Send me your incendiary video from 14 to 40 seconds long!
Video received! Choose a processing style for your video:
Neon boom
Bright party
It will take me some time to process. I'll send everything soon.
Everything worked out! Your video is available at https: // ...
And here's how the neural network «saw» our team:
Нейросеть распознает несколько человек


To create a bot, we used our own services:
Simple and convenient platform for developing chatbots, voice assistants and contact center automation systems.


AI service for chatbots analytics. Allows you to conduct a deeper analysis of human-robot dialogues and get a more accurate assessment of the effectiveness of the bot.


We create a hosting platform for the execution of computer vision models on any device. Models are executed on our servers and are available via REST API

Vision Hub

zDialog фреймворк
OneDash сервис

Development process

Step 01
Trained the neural network to «see» and segment body parts and clothes on video
Step 02
Step 03
Step 04
We tested the service, made necessary debugging
Step 05
Step 06
Wrote a user guide on how to best shoot videos
Launched the service
Trained the neural network to «see» and segment furniture on video
Made three different effects for the video

Difficulties of the project

The custom videos were of low quality, with poor lighting.
To improve the picture, we used four computer vision models. They predicted the position of an object in the frame, making the image clearer.
The neural network could color different frames in different ways; noises appeared in the video.
We have improved the work of the algorithm that was responsible for the clarity of the picture.
It was a time-consuming process: a 15- second video would take 15 minutes to process. This created a risk that the user would not wait or that the load on the serve would become too great
We indicated to the user exactly how much time was needed to queue a video to inform them of possible wait times. Added additional spare capacity which made provided stable operation

Project results

A ton of new knowledge is our largest and most complex project related to image segmentation on video
The client was satisfied and decided to launch a similar service for users in Ukraine and Belarus

Project team

2 project managers
3 backend developers
Technical Director
2 data analytics
ESSA logo

What we learned

The implementation of a complex combination of machine vision models
Process video recordings of different quality, including compressed algorithms
Contact us