research
∙
04/27/2021
MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions
Deep learning has made significant impacts on multi-view stereo systems....
share
research
∙
10/02/2020
Semantic MapNet: Building Allocentric SemanticMaps and Representations from Egocentric Views
We study the task of semantic mapping - specifically, an embodied agent ...
research
∙
06/11/2019
Clouds of Oriented Gradients for 3D Detection of Objects, Surfaces, and Indoor Scene Layouts
We develop new representations and algorithms for three-dimensional (3D)...
research
∙
04/09/2019
Embodied Visual Recognition
Passive visual systems typically fail to recognize objects in the amodal...
research
∙
02/18/2019
Multi-layer Depth and Epipolar Feature Transformers for 3D Scene Reconstruction
We tackle the problem of automatically reconstructing a complete 3D mode...
research
∙
10/23/2018
A Fusion Approach for Multi-Frame Optical Flow Estimation
To date, top-performing optical flow estimation methods only take pairs ...
research
∙
07/26/2017