1 code implementation • ECCV 2020 • Zak Murez, Tarrence van As, James Bartolozzi, Ayan Sinha, Vijay Badrinarayanan, Andrew Rabinovich
Traditional approaches to 3D reconstruction rely on an intermediate representation of depth maps prior to estimating a full 3D model of a scene.
Ranked #1 on Depth Estimation on ScanNet
1 code implementation • ECCV 2020 • Ayan Sinha, Zak Murez, James Bartolozzi, Vijay Badrinarayanan, Andrew Rabinovich
Cost volume based approaches employing 3D convolutional neural networks (CNNs) have considerably improved the accuracy of MVS systems.
Ranked #1 on Depth Estimation on ScanNetV2
no code implementations • 12 Sep 2019 • Prajwal Chidananda, Ayan Sinha, Adithya Rao, Douglas Lee, Andrew Rabinovich
2D Key-point estimation is an important precursor to 3D pose estimation problems for human body and hands.
no code implementations • 21 Jun 2018 • Ayan Sinha, Zhao Chen, Vijay Badrinarayanan, Andrew Rabinovich
We demonstrate gradient adversarial training for three different scenarios: (1) as a defense to adversarial examples we classify gradient tensors and tune them to be agnostic to the class of their corresponding example, (2) for knowledge distillation, we do binary classification of gradient tensors derived from the student or teacher network and tune the student gradient tensor to mimic the teacher's gradient tensor; and (3) for multi-task learning we classify the gradient tensors derived from different task loss functions and tune them to be statistically indistinguishable.
1 code implementation • CVPR 2017 • Ayan Sinha, Asim Unmesh, Qi-Xing Huang, Karthik Ramani
3D shape models are naturally parameterized using vertices and faces, \ie, composed of polygons forming a surface.
no code implementations • NeurIPS 2016 • Ayan Sinha, David F. Gleich, Karthik Ramani
Collaborative filtering is a popular technique to infer users' preferences on new content based on the collective information of all users preferences.
no code implementations • 22 Feb 2017 • Ayan Sinha, Justin Lee, Shuai Li, George Barbastathis
Deep learning has been proven to yield reliably generalizable answers to numerous classification and decision tasks.
no code implementations • CVPR 2016 • Ayan Sinha, Chiho Choi, Karthik Ramani
Our matrix completion algorithm uses these 'spatio-temporal' activation features and the corresponding known pose parameter values to to estimate the unknown pose parameters of the input feature vector.
no code implementations • ICCV 2015 • Chiho Choi, Ayan Sinha, Joon Hee Choi, Sujin Jang, Karthik Ramani
Specifically, we recast the hand pose estimation problem as the cold-start problem for a new user with unknown item ratings in a recommender system.