Akshay Gadi Patil


Akshay Gadi Patil
Ph.D Student

GrUVi Lab
School of Computing Science
Simon Fraser University

Office: TASC-1 8004

About Me

Hello! I am a fourth year Ph.D student advised by Prof. Hao (Richard) Zhang.
My research revolves around the Geometric application of Deep Learning for content creation and understanding.
Specifically, I focus on structural generation of 3D Indoor Scenes and 2D Layouts.

I was an Applied Scientist Intern at Amazon, from Dec 2018 to Mar 2019.

Prior to joining SFU, I completed my M.Tech in Electrical Engineering (Signal Processing) from the Indian Institute of Technology Gandhinagar in 2016. I have also spent time as a visiting student at JAIST, Japan .


 DR-KFS, a Differentiable Visual Similarity Metric for 3D Shape 
Reconstruction, is on arXiv. Check it out.

 Paper on generating document layouts, READ, completed in March 2019, 
is now on arXiv (some logistic delays within Amazon). Read READ!

Our TOG paper will be presented at SIGGRAPH 2019, in LA.

 Applied Scientist Intern @ Amazon (till Mar'19) 

 Presented a  poster  on our recent TOG paper @ ARD Seattle. 

Paper on Recursive Neural Network Architecture for Indoor Scenes was
conditionally accepted to TOG. Details coming soon!

Paper on Language-Driven Scene Synthesis was accepted to SIGGRAPH-Asia.
More details on the Project Page.

I was a Student Volunteer for the 45th ACM SIGGRAPH conference here in Vancouver, B.C.

Publications [Scholar]

"Si falta pasiĆ³n no se encuentra la victoria".

- Rafa


DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction

Jiongchao Jin, Akshay Gadi Patil, Zhang Xiong, Hao Zhang
READ: Recursive Autoencoders for Document Layout Generation
Akshay Gadi Patil, Omri Ben-Eliezer, Or Perel, Hadar Averbuch-Elor
arXiv , Supplementary

GRAINS: Generative Recursive Autoencoders for INdoor Scenes
Manyi Li, Akshay Gadi Patil, Kai Xu, Siddhartha Chaudhuri, Owais Khan, Ariel Shamir, Changhe Tu, Baoquan Chen, Daniel Cohen-Or, Hao Zhang
Transactions on Graphics (Special Issue of SIGGRAPH 2019)

Project Page
Language-Driven Synthesis of 3D Scenes Using Scene Databases
Rui Ma*, Akshay Gadi Patil*, Matthew Fisher, Manyi Li, Sören Pirk,
Binh-Son Hua, Sai-Kit Yeung, Xin Tong, Leonidas Guibas, Hao Zhang
SIGGRAPH-Asia, Tokyo, 2018 (*Co-first Authors)

Project Page, Media , On Twitter

Automatic Content-Aware Non-Photorealistic Rendering of Images
Akshay Gadi Patil, Shanmuganathan Raman
International Symposium on Visual Computing (ISVC), Las Vegas, 2016.
Tone Mapping HDR Images Using Local Texture and Brightness Measures
Akshay Gadi Patil, Shanmuganathan Raman
International Conference on Computer Vision and Image Processing (CVIP), 2016.


Primary Reviewer for: ICLR(2020), CGF (since 2020), TVCG (since 2019), The Visual Computer (since 2018)

Student Volunteer at SIGGRAPH'18