Mayank Agarwal

I am a Masters in Computer Vision student at the Robotics Institute, Carnegie Mellon University, where I am advised by Prof. Shubham Tulsiani. I am currently working on Sparse-View 3D Reconstruction.

Before joining CMU, I worked as a Deep Learning Engineer at Flixstock, primarily working on Generative Adversarial Networks for photorealistic image editing to solve business problems in the fashion industry. Previously, I have also developed quant tools to analyze financial datasets at D.E. Shaw.

Before that, I was a research intern at Video Analytics Lab, Indian Institute of Science, advised by Prof. Venkatesh Babu. During my Bachelor's thesis at IISc, I primarily worked on single-view 3D point cloud reconstruction. I graduated from Birla Institute of Technology and Science, Pilani, India with a major in Computer Science in 2018.

Email  /  Google Scholar  /  Github /  Medium /  Twitter

profile photo
Research

I'm primarily interested in computer vision, computer graphics, machine learning, and image processing.

Papers (* equal contribution)
CAPNet CAPNet: Continuous Approximation Projection for 3D Point Cloud Reconstruction Using 2D Supervision
KL Navaneet*, Priyanka Mandikal*, Mayank Agarwal, R.Venkatesh Babu
AAAI Conference on Artificial Intelligence (AAAI), 2019
paper / code
3D-LMNet 3D-LMNet: Latent Embedding Matching for Accurate and Diverse 3D Point Cloud Reconstruction from a Single Image
Mayank Agarwal*, Priyanka Mandikal*, KL Navaneet*, R.Venkatesh Babu
British Machine Vision Conference (BMVC) , 2018
paper /  demo /  code

Source taken from here