Publications
Sculpting with Words (NeurIPS)
Published in the Machine Learning for Creativity and Design 2021. In this work we present an interactive framework for text-guided 3D mesh generation. Our tool integrates the power of large multimodal pre-trained models (i.e. CLIP) and differentiable rendering into a traditional 3D sculpting environment.
The Animation Transformer (ICCV)
We propose the Animation Transformer (AnT) which uses a transformer-based architecture to learn the spatial and visual relationships between segments across a sequence of images. AnT enables practical, state-of-art AI-assisted colorization for professional animation workflows and is publicly accessible as a creative tool in Cadmium.
Transformers in Computer Vision: Farewell Convolutions!
This article aims to introduce/refresh the main ideas behind Transformers and to present the latest advancements on using these models for Computer Vision applications.
Generating Images from Prompts using CLIP and StyleGAN
In this article I propose a simple yet powerful architecture to use CLIP together with StyleGAN to generate images from prompts.