Day to Day:
This person will be joining a cutting-edge computer vision AI research team creating foundation models in an open-source environment. This person will help build demos showcasing new capabilities found in data models, specifically rendering videos and images, applying certain transformations, and taking demo experiences to the next level to render cool effects.
Program Overview:
A foundation model towards solving promptable visual segmentation in images and videos. We build a data engine, which improves model and data via user interaction, to collect the largest video segmentation dataset to date. Our model is a simple transformer architecture with streaming memory for real-time video processing. SAM 2 trained on our data provides strong performance across a wide range of tasks. In video segmentation, we achieve better accuracy with 3x fewer interactions compared to prior approaches. In image segmentation, our model is more accurate and 6x faster than the Segment Anything Model (SAM). We believe that our data, model, and insights will serve as a significant milestone for video segmentation and related perception tasks. We are releasing a version of our model, the dataset, and an interactive demo.
Requirements:
Pluses:
Pay:
$60hr - $70hr