research
∙
05/18/2023
MVPSNet: Fast Generalizable Multi-view Photometric Stereo
We propose a fast and generalizable solution to Multi-view Photometric S...
share
research
∙
03/18/2023
LossMix: Simplify and Generalize Mixup for Object Detection and Beyond
The success of data mixing augmentations in image classification tasks h...
research
∙
03/13/2023
A Surface-normal Based Neural Framework for Colonoscopy Reconstruction
Reconstructing a 3D surface from colonoscopy video is challenging due to...
research
∙
11/19/2022
A Practical Stereo Depth System for Smart Glasses
We present the design of a productionized end-to-end stereo depth sensin...
research
∙
10/04/2022
Toward Edge-Efficient Dense Predictions with Synergistic Multi-Task Neural Architecture Search
In this work, we propose a novel and scalable solution to address the ch...
research
∙
04/05/2022
Leveraging Disentangled Representations to Improve Vision-Based Keystroke Inference Attacks Under Low Data
Keystroke inference attacks are a form of side-channel attacks in which ...
research
∙
03/14/2022
VPFusion: Joint 3D Volume and Pixel-Aligned Feature Fusion for Single and Multi-view 3D Reconstruction
We introduce a unified single and multi-view neural implicit 3D reconstr...
research
∙
11/19/2021
ColDE: A Depth Estimation Framework for Colonoscopy Reconstruction
One of the key elements of reconstructing a 3D mesh from a monocular vid...
research
∙
12/06/2020
Any-Width Networks
Despite remarkable improvements in speed and accuracy, convolutional neu...
research
∙
09/12/2020
Revisiting the Threat Space for Vision-based Keystroke Inference Attacks
A vision-based keystroke inference attack is a side-channel attack in wh...
research
∙
08/27/2020
One Shot 3D Photography
3D photography is a new medium that allows viewers to more fully experie...
research
∙
08/27/2020
Reducing Drift in Structure from Motion using Extended Features
Low-frequency long-range errors (drift) are an endemic problem in 3D str...
research
∙
12/19/2019
Tangent Images for Mitigating Spherical Distortion
In this work, we propose "tangent images," a spherical image representat...
research
∙
11/22/2019
ViewSynth: Learning Local Features from Depth using View Synthesis
We address the problem of jointly detecting keypoints and learning descr...
research
∙
06/26/2019
Mapped Convolutions
We present a versatile formulation of the convolution operation that we ...
research
∙
05/21/2019
Convolutions on Spherical Images
Applying convolutional neural networks to spherical images requires part...
research
∙
04/15/2019
Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depth
Deep learning-based, single-view depth estimation methods have recently ...
research
∙
05/17/2018
Recurrent Neural Network for Learning DenseDepth and Ego-Motion from Video
Learning-based, single-view depth estimation often generalizes poorly to...
research
∙
05/11/2018
The Domain Transform Solver
We present a framework for edge-aware optimization that is an order of m...
research
∙
05/22/2016