384 citations · 424 across the 6 of their papers we have counts for
8 papers
Project Aria: A New Tool for Egocentric Multi-Modal AI Research
Jakob Engel, Kiran Somasundaram, Michael Goesele +71
Egocentric, multi-modal data as available on future augmented reality (AR) devices provides unique challenges and opportunities for machine perception. These future devices will ne…
ERF: Explicit Radiance Field Reconstruction From Scratch
Samir Aroudj, Steven Lovegrove, Eddy Ilg +3
We propose a novel explicit dense 3D reconstruction approach that processes a set of images of a scene with sensor poses and calibrations and estimates a photo-real digital model.…
LR-CNN: Local-aware Region CNN for Vehicle Detection in Aerial Imagery
Wentong Liao, Xiang Chen, Jingfeng Yang +4
State-of-the-art object detection approaches such as Fast/Faster R-CNN, SSD, or YOLO have difficulties detecting dense, small targets with arbitrary orientation in large aerial ima…
The Replica Dataset: A Digital Replica of Indoor Spaces
Julian Straub, Thomas Whelan, Lingni Ma +27
We introduce Replica, a dataset of 18 highly photo-realistic 3D indoor scene reconstructions at room and building scale. Each scene consists of a dense mesh, high-resolution high-d…
Background Subtraction with Real-time Semantic Segmentation
Dongdong Zeng, Xiang Chen, Ming Zhu +2
Accurate and fast foreground object extraction is very important for object tracking and recognition in video surveillance. Although many background subtraction (BGS) methods have…
Detail-Preserving Pooling in Deep Networks
Faraz Saeedan, Nicolas Weber, Michael Goesele +1
Most convolutional neural networks use some method for gradually downscaling the size of the hidden layers. This is commonly referred to as pooling, and is applied to reduce the nu…
Simplification of Multi-Scale Geometry using Adaptive Curvature Fields
Patrick Seemann, Simon Fuhrmann, Stefan Guthe +2
We present a novel algorithm to compute multi-scale curvature fields on triangle meshes. Our algorithm is based on finding robust mean curvatures using the ball neighborhood, where…
Virtual Rephotography: Novel View Prediction Error for 3D Reconstruction
Michael Waechter, Mate Beljan, Simon Fuhrmann +3
The ultimate goal of many image-based modeling systems is to render photo-realistic novel views of a scene without visible artifacts. Existing evaluation metrics and benchmarks foc…