43 citations · 115 across the 7 of their papers we have counts for
8 papers
Atlas: End-to-End 3D Scene Reconstruction from Posed Images
Zak Murez, Tarrence van As, James Bartolozzi +3
We present an end-to-end 3D reconstruction method for a scene by directly regressing a truncated signed distance function (TSDF) from a set of posed RGB images. Traditional approac…
DELTAS: Depth Estimation by Learning Triangulation And densification of Sparse points
Ayan Sinha, Zak Murez, James Bartolozzi +2
Multi-view stereo (MVS) is the golden mean between the accuracy of active depth sensing and the practicality of monocular depth estimation. Cost volume based approaches employing 3…
Efficient 2.5D Hand Pose Estimation via Auxiliary Multi-Task Training for Embedded Devices
Prajwal Chidananda, Ayan Sinha, Adithya Rao +2
2D Key-point estimation is an important precursor to 3D pose estimation problems for human body and hands. In this work, we discuss the data, architecture, and training procedure n…
Gradient Adversarial Training of Neural Networks
Ayan Sinha, Zhao Chen, Vijay Badrinarayanan +1
We propose gradient adversarial training, an auxiliary deep learning framework applicable to different machine learning problems. In gradient adversarial training, we leverage a pr…
Imaging through glass diffusers using densely connected convolutional networks
Shuai Li, Mo Deng, Justin Lee +2
Computational imaging through scatter generally is accomplished by first characterizing the scattering medium so that its forward operator is obtained; and then imposing additional…
SurfNet: Generating 3D shape surfaces using deep residual networks
Ayan Sinha, Asim Unmesh, Qixing Huang +1
3D shape models are naturally parameterized using vertices and faces, \ie, composed of polygons forming a surface. However, current 3D learning paradigms for predictive and generat…