Search Results for author:
Found 9 papers, 3 papers with code
Atlas: End-to-End 3D Scene Reconstruction from Posed Images
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
DELTAS: Depth Estimation by Learning Triangulation And densification of Sparse points
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
Efficient 2.5D Hand Pose Estimation via Auxiliary Multi-Task Training for Embedded Devices
2D Key-point estimation is an important precursor to 3D pose estimation problems for human body and hands.
Gradient Adversarial Training of Neural Networks
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.
SurfNet: Generating 3D shape surfaces using deep residual networks
3D shape models are naturally parameterized using vertices and faces, \ie, composed of polygons forming a surface.
Deconvolving Feedback Loops in Recommender Systems
Collaborative filtering is a popular technique to infer users' preferences on new content based on the collective information of all users preferences.
Lensless computational imaging through deep learning
Deep learning has been proven to yield reliably generalizable answers to numerous classification and decision tasks.
DeepHand: Robust Hand Pose Estimation by Completing a Matrix Imputed With Deep Features
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.
A Collaborative Filtering Approach to Real-Time Hand Pose Estimation
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.
