Featured Resource
Featured Case Study
Stuttgart AI, ML and Computer Vision Meetup
February 5, 2025 | 5:30 to 8:30 PM
When and Where
February 5, 2025 from 5:30 PM to 8:30 PM
Location
The Meetup will take place at Impact Hub Stuttgart, Quellenstraße 7a 70376 Stuttgart
Open World Scene Understanding and Interaction for Autonomous Cars
Tin Stribor Sohn
Porsche AG
Stay tuned for the talk abstract
Realistic 3D Asset Generation by Joint Diffusion in 2D and 3D
Yuxuan Xue
University of Tübingen
Creating realistic 3D objects and humans from a single image is a challenging problem. Recent 2D diffusion models can generate multiple views of 3D, but lack consistency across different views. Human-3Diffusion and Gen-3Diffusion leverage a pre-trained 2D diffusion model and a 3D diffusion model via a joint diffusion process that synchronizes two diffusion models at both training and sampling time. The synergy between the 2D and 3D diffusion models ensures the generalisation ability from the 2D diffusion prior and the multi view consistency from the 3D diffusion prior. With Human-3Diffusion and Gen-3Diffusion, people can easily generate realistic 3D avatars and objects with high-fidelity geometry and texture. The code and pre-trained models will be publicly released here.
Dataset Safari: Adventures from 2024’s Top Computer Vision Conferences
Harpreet Sahota
Voxel51
Datasets are the lifeblood of machine learning, driving innovation and enabling breakthrough applications in computer vision and AI. This talk presents a curated exploration of the most compelling visual datasets unveiled at CVPR, ECCV, and NeurIPS 2024, with a unique twist – we’ll explore them live using FiftyOne, the open-source tool for dataset curation and analysis.
Using FiftyOne’s powerful visualization and analysis capabilities, we’ll take a deep dive into these collections, examining their unique characteristics through interactive sessions. We’ll demonstrate how to:
- Analyze dataset distributions and potential biases
- Identify edge cases and interesting samples
- Compare similar samples across datasets
- Explore multi-modal annotations and complex label structures
Whether you’re a researcher, practitioner, or dataset enthusiast, this session will provide hands-on insights into both the datasets shaping our field and practical tools for dataset exploration. Join us for a live demonstration of how modern dataset analysis tools can unlock deeper understanding of the data driving AI forward.
Find a Meetup Near You
Join the AI and ML enthusiasts who have already become members
The goal of the AI, Machine Learning, and Computer Vision Meetup network is to bring together a community of data scientists, machine learning engineers, and open source enthusiasts who want to share and expand their knowledge of AI and complementary technologies. If that’s you, we invite you to join the Meetup closest to your timezone.
Tin Stribor Sohn
Porsche AG
Tin Stribor Sohn is a doctoral candidate and tech lead for vehicle data analytics at Porsche AG, dealing with scenario search and failure cause analysis for automated driving. Tin holds an MSc. in computer science and co-founder/CTO of an energy startup.
Yuxuan Xue
University of Tübingen
Yuxuan Xue is currently pursuing Ph.D. degree at the Univerisity of Tübingen, supervised by Prof. Dr. Gerard Pons-Moll. His research interests lie on perceiving human from real world and modelling into metaverse. He regularly published at top conferences and journal in machine learning and vision (ICCV, NeurIPS, ICLR, IJCV). He got the Best Student Paper Award at BMVC 2022 and also a research grant from OpenAI in 2024.
Harpreet Sahota
Voxel51
Harpreet Sahota is a hacker-in-residence and machine learning engineer with a passion for deep learning and generative AI. He’s got a deep interest in RAG, Agents, and Multimodal AI.