Internship: Point Cloud Panoptic Segmentation

Panoptic segmentation on point cloud data presents a new challenge in exploiting the merits of both detection and segmentation, with the aim of unifying instance segmentation and semantic segmentation in a single framework. However, an efficient solution for panoptic segmentation in the emerging domain of LiDAR point cloud is still an open research problem and includes many challenging situations. Understanding point cloud data is inherently an unordered list of points and therefore, traditional deep learning approaches can not be applied directly.

SAMP has access to a large amount of data to train machine learning models. However, the scans come from many different sites that may differ in their nature (Nuclear Plants, Oil and Gas plants, Chemical Plants, Manufacturing Plants) as well as the characteristics of the sensors. So data imbalance and redundancy are a systematic characteristic that arises when collecting large amounts of data. Understanding our data distribution helps in choosing the right set of data samples that are important for model training. Furthermore, data augmentation techniques are essential to avoid model overfitting.

You will be working with our automation team on improving our panoptic segmentation pipeline. The objective of this ambitious internship is to scale up the performance of our current AI models for point cloud segmentation. Your tasks will include:

  • Understanding and familiarizing with SAMP AI models for panoptic semantic segmentation, as well as our internal datasets
  • Developing and evaluating deep learning algorithms on panoptic segmentation of point cloud dataset
  • Investigating different data augmentation techniques and analyze their effects on our model performance.

Overall, you are expected to be proactive and contribute with your ideas to improve the results.

  • Contract Type: Internship (Between 5 and6 months)
  • Start Date: Jan-Feb 2022
  • Location: Paris 6ème, France 
  • Education Level: Master’s Degree or Equivalent
  • Salary: 1200€ gross / month
  • Advisor: Nachwa Bakr, PhD and Shivani Shah, PhD
  • Possible partial remote
The personal data collected by means of the forms on this website will be kept and processed by Samp, for reasons of recruitment purposes only. Such data will be kept for a duration of maximum 24 months and processed in accordance with the provisions of the General Data Protection Regulation (GDPR) and any compulsory provisions of applicable data privacy laws. The data will be kept and processed on France. The website users can exercise their data subject rights by contacting the privacy officer of Samp at


Samp is a deep tech startup that helps large industrial facilities successfully go through constant modernization required to meet the fundamental challenges of safety and sustainability.
At Samp, we believe that our ability as a society to collectively transition to a sustainable world first and foremost depends upon how we will manage our large industrial facilities.
We provide software solutions that capture and exposes a reliable 3D model of the facilities to all players, a “Digital Twin”.
We are backed by one of Europe’s leading VC firm – Entrepreneur First – and are based in Station F.

Laurent, our CEO, has a PhD and 15 years of experience in the Energy industry. He has held important positions in companies like ENGIE and Wood Plc. Most recently he was
Technical Director at Dassault Systèmes, in charge of the solutions for the Energy & Materials division.

Shivani, our CTO, has a PhD in Machine Learning from CEA Saclay.
Our team is mentored by a team of advisors composed of senior academic and business experts having occupied executive positions in large energy companies.


Station F
5 Parvis Alan Turing
75013 Paris

Laurent Bourgouin (CEO)

What can you expect
from a demo with SAMP?