Aakash KT


Ph.D candidate at IIIT-H, Aug 2020 - May 2024 (Expected)

I am a final year Ph.D candidate at CVIT, IIIT Hyderabad, supervised by Dr. P. J. Narayanan (Funded by the KCIS fellowship).
Previously, I completed my MS by research at IIIT Hyderabad, which is also where I completed my BTech in Computer Science Engineering.
My research involves playing around with the light transport equation towards real-time performance, differentiable rendering and neural rendering.

During my Ph.D, I have had the pleasure of collaborating with Eric Heitz & Jonathan Dupuy during their time at
Unity Research, Grenoble.
I have also been fortunate to have worked as a Research Scientist Intern at Meta Reality Labs in Pittsburgh, with Giljoo Nam.

Resume / Email / Google Scholar / Twitter / LinkedIn


Apr 1, 2024 I am taking a few guest lectures for the Computer Graphics course at IIT Jodhpur. These lectures will be on physically based rendering with ray tracing - following our course at IIIT Hyderabad. Many thanks to Prof. Avinash for the invitation!
Jan 2, 2024 I am teaching Introduction to Computer Graphics course at IIIT Hyderabad with Prof. PJN. We have revamped this course to teach Physically Based Rendering, following the excellent reference PBRT-v3 and Prof. Wojciech Jarosz’s rendering course at Darthmouth.
Sep 26, 2023 Our paper on combining RIS with projected solid angle sampling was accepted at SIGGRAPH Asia Technical Communications!
Sep 6, 2023 I will present a summary of my PhD thesis at the Doctoral Consortium of SIGGRAPH Asia 2023 in Sydney, Australia.
May 26, 2023 Our work during my internship at Meta Reality Labs, Pittsburgh has been accepted to EGSR 2023, and will also be published in CGF Journal!
May 5, 2022 We received the best paper award at I3D for our paper “Bringing Linearly Transformed Cosines to Anisotropic GGX”! NVIDIA was generous to gift us a RTX 3090 for this. Thank you!
Mar 29, 2022 I will be joining Meta Reality Labs, Pittsburgh (formerly Facebook Reality Labs) as a Research Scientist Intern in August. I will be working in Yaser Sheikh’s team, with Giljoo Nam. Looking forward to some exciting work on Photorealistic Telepresence!
Mar 10, 2022 Our paper “Bringing Linearly Transformed Cosines to Anisotropic GGX” has been accepted to I3D 2022! This work was in collaboration with Eric Heitz and Jonathan Dupuy from Unity Research Grenoble.
Mar 4, 2022 Our work “Precomputed Radiance Transfer Using Transfer Textures” has been accepted as a poster to EG 2022.
Jun 5, 2021 Our paper “Fast Analytic Soft Shadows from Area Lights” has been accepted to EGSR 2021!
Aug 1, 2020 I have joined as a Ph.D student at CVIT, IIIT Hyderabad, supervised by Dr. P. J. Narayanan. My Ph.D is funded by the KCIS fellowship. Curious as to why I decided to do this? See here.
Feb 1, 2020 I was to join the GraphDeco research group @ Inria (Sophia Antipolis, France), as a pre-doctoral candidate from September 2020, supervised by Dr. George Drettakis and Dr. Adrien Bousseau. This was unfortunately rescinded due to COVID.

Selected Publications

  1. Combining Resampled Importance and Projected Solid Angle Samplings for Many Area Light Rendering

    Ishaan Shah*Aakash KT*, and P. J. Narayanan
    ACM SIGGRAPH Asia 2023, Technical Communications (Formerly Technical Briefs)

    We identify the core issue for the high run-times of a naive combination of RIS and projected solid angle sampling. We then reformulate RIS for a better integration with projected solid angle sampling, achieving the state-of-the-art in many area light rendering.

  2. Analytical & Neural approaches to Physically Based Rendering

    Aakash KT
    ACM SIGGRAPH Asia 2023, Doctoral Consortium

    Summary of my PhD thesis, including two extensions to LTCs and the extension of NRC for efficient hair rendering.

  3. Accelerating Hair Rendering by Learning High-Order Scattered Radiance

    Eurographics Symposium on Rendering (EGSR) 2023, Computer Graphics Forum (CGF) Vol. 42, No. 4

    Efficiently and accurately rendering hair accounting for multiple scattering is a challenging open problem. We present a technique to infer the higher order scattering in hair in constant time within the path tracing framework, while achieving better computational efficiency.

  4. Bringing Linearly Transformed Cosines to Anisotropic GGX

    ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (I3D) 2022, PACM-CGIT, Best Paper Award

    We present an extension to LTCs for anisotropic GGX, in the context of real-time analytic area light shading. Our approach robustly fits LTC matrices to anisotropic GGX and ensures artefact free rendering. The end result is a 84 LUT parameterized by the elevation and azimuth of view vector and the roughness in x and y directions.

  5. Fast Analytic Soft Shadows from Area Lights

    Eurographics Symposium on Rendering (EGSR) 2021, DL-only track

    We present an analytical solution for soft shadows from area lights, which naturally produces noise-free renderings as compared to equivalent stochastic methods. A structured approach to analytically compute soft shadows from spherical projections of lights and occluders with any 3D shape and efficiently for convex 3D shapes.

  6. Exploring Data Driven Graphics for Interactivity

    Aakash KT, and P. J. Narayanan
    IIIT-H, Master’s Thesis

  7. A Flexible Neural Renderer for Material Visualization

    ACM SIGGRAPH Asia 2019, Technical Briefs

    Photo realism in computer generated imagery is crucially dependent on how well an artist is able to recreate real-world materials in the scene. We propose a convolutional neural network based workflow which generates high-quality ray traced material visualizations on a shaderball, in real-time.