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

Research

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

Papers (* equal contribution)

	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: 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