Siddhant Prakash

Siddhant is a Research Scientist at Adobe Research. His primary research interests lies in computer vision and graphics with an aim to understand how humans interact with the visual world. He is currently looking into multimodal language models to bridge the interface between natural languages and visual computing.

Prior to Adobe, Siddhant was a Research Fellow at University College London, where he worked at the Virtual Environments and Computer Graphics (VECG) group on photorealistic rendering for mixed reality on head-mounted displays, leveraging machine learning and neural rendering techniques. Siddhant completed his Ph.D. with Dr. George Drettakis in the GraphDeco group at INRIA Sophia Antipolis, studying photorealistic rendering of real environments from captured media. He holds a master’s in computer science from Arizona State University, where he developed algorithms for mobile mixed-reality systems, and a B.Tech (Hons.) from IIIT Hyderabad. Siddhant has published at top computer graphics journals including TVCG, TOG, PACMCGIT and CAG. More details about his work can be found here.

His interest in visual computing stems from his love for photography, and he enjoys capturing candid moments, particularly in travel and event photography. You can checkout few of his captures on his Photo Blog.