NewEvery arXiv paper, its researchers & institutions — mapped.
the archive

#augmented reality

5 results
cs.CV2019

Image-based marker tracking and registration for intraoperative 3D image-guided interventions using augmented reality

Andong Cao, Ali Dhanaliwala, Jianbo Shi +2

The paper presents a method that uses radio‑opaque QR‑code markers and a Microsoft HoloLens to quickly register and align pre‑operative CT scans with a patient’s anatomy in the ope…

#augmented reality#image registration#marker tracking#surgical navigation
cs.CV2019

Editing Text in the Wild

Liang Wu, Chengquan Zhang, Jiaming Liu +4

The paper introduces SRNet, an end‑to‑end network that can replace or modify words in natural images while preserving the original text style and background, using separate modules…

#text editing#image synthesis#style transfer#background inpainting
cs.HC2019

Origin-Destination Flow Maps in Immersive Environments

Yalong Yang, Tim Dwyer, Bernhard Jenny +3

The paper studies how to visualize origin‑destination flow data in immersive VR/AR settings, comparing 2D and 3D encodings and finding that raised 3D flows on globes improve accura…

#flow maps#immersive visualization#virtual reality#augmented reality
cs.CV2019

Semi-Automatic Labeling for Deep Learning in Robotics

Daniele De Gregorio, Alessio Tonioni, Gianluca Palli +1

The paper introduces Augmented Reality Semi‑automatic labeling (ARS), a method that uses a robot‑mounted camera and an AR pen to quickly generate large, accurately labeled image da…

#semi-automatic labeling#augmented reality#robotic vision#object detection
cs.CV2019

HDM-Net: Monocular Non-Rigid 3D Reconstruction with Learned Deformation Model

Vladislav Golyanik, Soshi Shimada, Kiran Varanasi +1

The paper presents HDM-Net, a deep neural network that learns a deformation model to enable dense 3D reconstruction of non‑rigid objects from a single monocular view without requir…

#monocular 3d reconstruction#non-rigid shape#deep learning#deformation modeling