Research & Education

SHARP - 3D Gaussian Scene Prediction is an AI tool focused on monocular view synthesis. Its primary function is to generate detailed 3D scenes using only 2D input images. This capability makes it particularly useful for researchers and developers engaged in the fields of 3D reconstruction and the advancement of AI models. The tool facilitates experimentation with novel approaches to understanding and recreating three-dimensional environments from limited visual data.

ComfyUI-Florence2 is a tool specifically designed for running inference using the Microsoft Florence-2 Vision Language Model (VLM). This model utilizes a prompt-based methodology to handle various vision and vision-language tasks. Users can provide text prompts to direct the model to perform functions such as generating captions for images, detecting objects within visual content, and segmenting different parts of an image. It serves as an interface for leveraging the capabilities of the Florence-2 VLM.

Lexicon Quest is a vocabulary learning app that gamifies the process by turning it into an RPG adventure. Users battle monsters by solving word puzzles. It uses SM-2 spaced repetition, similar to Anki, and supports seven languages. The app works offline and is free to use.