Articles by Arnaud Hillen
3D Transformations: What are they used for in data annotation?
Use of 3D Transformations in 3D Data Annotation 3D transformations play a significant role in 3D data annotation, essential for training high-quality, safe deep learning models. 3D transformations are fundamental mathematical operations used in various scientific and technological fields, predominantly computer graphics and robotics. They [...]
7 State-Of-The-Art Point Cloud Models for Autonomous Driving
Over the past couple of years most state-of-the-art computer vision (deep learning) models have converged to use the transformer architecture. This trend has also emerged in deep learning models that work on point clouds (or both point clouds and images). However, these models are still harder to generalize to [...]
The Segments.ai Python SDK: A closer look
In this blog post we will go over the design decisions and features of the Segments’ Python SDK. Most of our users at Segments.ai use the platform to get labeled data to train a deep learning model. So most of them are pretty technical. Being able to integrate with [...]
Image to point cloud with Point-E
Just before Christmas, OpenAI published its Point-E model. During the holidays, we took it for a spin and experimented with how easy it would be to integrate the model into a Segments.ai workflow. Read with me, or give it a run for its money yourself. Colab notebook: ? Point-E [...]
Introducing Text Labeling
This blog is about a part of the Segments platform that is no longer available today. If you have any questions about this, please contact hello@segments.ai. Segments.ai has great labeling tools for computer vision. As multimodal learning is becoming increasingly important, even computer vision teams sometimes need to label other [...]
