Nithin Raghavan

I am a second-year PhD student at UC San Diego working in Dr Ravi Ramamoorthi's group. I completed my undergraduate studies at UC Berkeley in Applied Mathematics and Computer Science. I was also part of Dr Ren Ng's group, which is a part of the Berkeley AI Research Group.

My research interests include deep learning optimization, graphics, hardware acceleration and parallelization. My Berkeley alumnus website can be found here.

Email  /  Resume  /  LinkedIn  /  GitHub  /  Google Scholar

We present the first image-conditioned diffusion model for neural materials, and show an extension to text conditioning. To do this, we define a universal basis for neural materials as 16-channel feature textures, and train a conditional diffusion model for generating neural materials in this basis from flash images, natural images and text prompts. To our knowledge, our work is the first to enable single-shot neural material generation from arbitrary text or image prompts.

PRT-inspired hybrid neural-wavelet architectures trained on images can learn a scene's global illumination light transport tensor. Decoupling relighting from scene information as well as prediction in an orthonormal basis enable generalization to novel view and novel lighting conditions for many complex effects, such as rotating caustics.

Template borrowed from Jon Barron's website.