I am Aradhya, a Research Scientist at Adobe’s Media and Data Science Research Lab. My research focuses on Computer Graphics and Vision, with a strong interest in Generative AI and Multi-Modal Learning.

Previously, I worked extensively in Computer Graphics, specializing in 3D Reconstruction and Rendering in association with Graphics Research Group, IIITD. My works focus on different modalities and leveraging deep learning methods for 3D synthesis and reconstruction. My projects have spanned various aspects of 3D synthesis, including reconstruction from a single image, video-based reconstruction, and point cloud generation using Generative AI. A list of my works can be found here.

Currently, my work revolves around multi-modal learning, where I aim to develop methods that bridge the gap between different modalities and improve the performance of downstream tasks and general understanding of the world.