Our Visit at International Conference on Computer Vision (ICCV) 2023

Paradox Cat

TECH BLOG

Our Visit at International Conference on Computer Vision (ICCV) 2023

PARADOX CAT at #ICCV2023 🥐

Dr. Johan von Forstner

AI R&D Architect @ PARADOX CAT GmbH

International Conference on Computer Vision Oral Session
One of the oral sessions, Photo: ICCV

In October 2023, I attended the ICCV in Paris—one of the top global conferences in Computer Vision. Representing Paradox Cat’s AI division, which focuses on interior sensing and HMI systems for vehicles, I explored the latest research trends and innovations in the field. A particularly insightful tutorial covered the In-Camera rendering pipeline, highlighting how raw sensor data is transformed into images using modern AI techniques. The conference showcased a wide range of interdisciplinary work, underlining how rapidly the field is evolving and blending into other domains.

Overview

Attending ICCV 2023 in Paris

Johan standing infront of a ICCV23 banner
Finally arrived at the entrance to ICCV

In October 2023, I had the great opportunity to join the International Conference on Computer Vision (ICCV), one of the top scientific conferences in the Computer Vision field, which was held in Paris this year. Our AI division at Paradox Cat is working on new technologies for interior sensing and HMI interaction in vehicles, so joining ICCV was a perfect way to learn about the latest research in the field using my Paradox Cat training budget.

Kicking Off with Cameras and Algorithms

After getting off the train on which I had been speeding through the French countryside at 320 km/h, I headed directly to the conference venue at Paris Expo Porte de Versailles, where the workshops and tutorial sessions were already ongoing. I joined the tutorial on Understanding the In-Camera Rendering Pipeline and the Role of AI/Deep Learning, which gave an extensive background on how modern cameras perceive the world and which algorithms are needed to turn the raw sensor output into beautiful images.

Main Conference Highlights

The following three days constituted the main conference, with two tracks of oral sessions, as well as poster sessions in between. Certainly by now, it became clear that the field of Computer Vision and AI is really exploding — with many poster sessions rivaling the Paris Métro in terms of crowding, it was not always easy to push one’s way through towards the poster one wanted to see. Especially presentations from the well-known Big Tech companies and the award-winning papers like Tracking Everything Everywhere All at Once, Segment Anything and ControlNet received their well-deserved attention.

many people looking at the poster session at ICCV23
Packed poster session at ICCV 2023

Interdisciplinary Trends and Insights

It was also interesting to see that Computer Vision is becoming very interdisciplinary, in the sense that many methods are not just bound to specific problems, but are often applied all across the field and combined in new creative ways. This also meant that it probably became pretty hard for the conference organizers to group the papers into distinct sessions, and there really was something interesting in almost every session.

Inspiring Keynotes and Takeaways

Besides the oral and poster sessions, the final two days also incorporated two invited keynote sessions. Especially the talk from Pushmeet Kohli (Google DeepMind) was very inspiring, giving an insight to how DeepMind is using AI to help solve hard problems in science, such as their recent success predicting protein structures with AlphaFold.

HuggingFace 🤗 Open Source AI community event at STATION F
HuggingFace 🤗 Open Source AI community event at STATION F
johan and a llama infant of iccv
Trying to talk to the LLaMAs at the entrance

Merci, Paris!

Au revoir, et merci beaucoup, Paris 🥐🇫🇷!
Thanks a lot to the ICCV 2023 organizers for this great event, and thank you to Paradox Cat for letting me participate! I hope that we can also present some of our own work at a future conference.

Related articles

Machine Learning systems for HMI interaction

Machine Learning Systems for HMI

As a company that specializes in in-cabin AI applications, we hosted a World CafĂŠ session on the topic of architecting robust machine learning systems for HMI interaction within autonomous vehicles, moderated by Johan von Forstner (Principal Machine Learning Engineer) and Alexander Schaub (Director Development).

Follow us on our platforms!

If you want to be up-to-date feel free to follow us on our social media channels like Instagram, LinkedIn and Medium!

Latest Blog Post

How an AOSP training changed our perspective

Paradox Cat

TECH BLOG

How an AOSP training changed our perspective

From apps to Operating Systems

Fernando Gallego

Software Architect @ PARADOX CAT GmbH. Android Expert. Curious mind.

aosp title image
Image generated with DALL-E 3

Paradox Cat recently offered an exclusive 40-hour training on the Android Open-Source Project (AOSP), including a specialized focus on Android Automotive. This hands-on course, led by an expert in embedded systems, allowed participants to create custom device configurations, build kernels, modify SELinux policies, and explore Android’s architecture in-depth. By experimenting in a safe cloud-based environment, developers gained practical experience in AOSP customization and Android Automotive components like the Vehicle HAL. The training provided valuable insights into the complexities of AOSP, expanding knowledge for better decision-making in client projects. This opportunity highlights the importance of continuous learning and hands-on experience in the evolving world of Android development.

Overview

Exclusive AOSP Training Opportunity at Paradox Cat: Learning from Industry Experts

Being part of Paradox Cat means that from time to time you get to do some specialisation trainings on some technologies that not so many people get access to. In our case we had the opportunity to participate in an exclusive online training course about the topics most of us need for working with our customers. This time we did a 40-hour training on Android Open-Source Project (AOSP) with a dedicated day on Android Automotive given by an expert on embedded systems that has been in the industry for so many years already.

During this course we were able to listen to the lessons and then get our hands dirty trying the concepts ourselves on a preconfigured remote machine in the cloud (that made the setup for the course a breeze). It is proven that when you want to study something new, listening to a few lessons is not enough. We developers learn by doing and tinkering, and to do so for this course, we had a safe sandboxed environment to try out the commands we just learned, change some parameters, experiment, etc. and see the results ourselves without the fear of breaking our system.

Building and Customizing Android: Creating a New Product and Implementing Key Concepts

We touched on many topics involved in the building and customization of such a complex operating system like Android. We started by creating a new “product”, this means we created a new device configuration that allowed us to customize it by adding new packages, services and features.

Once we had this new “product” we applied all the things we saw during the lessons. From replacing the kernel with a new one we built from scratch, looking at the startup scripts and adding a new booting animation, to adding new modules and system services, modifying SELinux policies, adding a new HAL and calling JNI code. Then, for the Automotive part, we looked at the Vehicle HAL, vendor properties and the Car Service.

Enhancing Customer Projects with AOSP Knowledge: The Value of Expert Guidance and Hands-On Learning

By getting this knowledge we could be more effective for our customer project and make more informed decisions about the development of some parts of the system where we are involved. Since AOSP doesn’t really provide a lot of public documentation, it is comforting to have someone who understands it to explain to you the most difficult parts and be able to ask questions. And even better, that you get to do it yourself.

Summary

All in all, it was a lot of content condensed in just 40 hours, which means we had to review and play ourselves afterwards, just to get the most of it. However, I think it was very useful and allowed us to understand at a lower level how AOSP works and how the overall architecture is designed to work on mobile devices. As an app developer, it is completely another Android world that you don’t get to see when you create mobile applications. It means really getting into the nitty gritty details of an operating system, and if you have never done it before, it is both exciting and daunting at the same time, but if you are eager to learn new things outside of your comfort zone, this is your place. I am very happy that Paradox Cat gave me this opportunity to take this training and expand my knowledge, enabling me to grow as a Software Engineer.

Follow us on our platforms!

If you want to be up-to-date feel free to follow us on our social media channels like Instagram, LinkedIn and Medium!

Latest Blog Post

International Conference on Computer Vision Oral Session

Paradox Cat TECH BLOG Our Visit at International Conference on Computer Vision (ICCV) 2023 PARADOX CAT at #ICCV2023 🥐 Johan von Forstner