Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page

Johannes Hoster

dblp:347/2303 · DBLP profile ↗
← Back
1ranked-venue papers
1as first author
1since 2021 · last 2023
0000-0002-0630-4967ORCID · reported

Domains — the database's venue-derived domains; a paper can count in several

Graphics, computer vision, multimedia, augmented reality and games · 1 · 1 first-author · 1 since 2021Human-computer interaction and ubiquitous computing · 1 · 1 first-author · 1 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Computer graphics and multimedia
1 paper
Visual content generation and editing · 100%
Human-computer interaction and pervasive computing
1 paper
Immersive interaction · 100%
Artificial intelligence
1 paper
3D vision · 100%

Topics — the 2 heaviest of 3, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Visual content generation and editing
style transfer
0.712023
Style-aware Augmented Virtuality Embeddings (SAVE) · VR 2023
Immersive interaction › mixed reality
augmented virtuality
0.712023
Style-aware Augmented Virtuality Embeddings (SAVE) · VR 2023

Methods — techniques the papers use, named apart from their topics

style transfer · 2.0real-time superimposition · 2.0mesh retrieval · 2.0
YearPublicationVenuePosition
2023 Style-aware Augmented Virtuality Embeddings (SAVE)
abstract
We present an augmented virtuality (AV) pipeline that enables the user to interact with real-world objects through stylised representations which match the VR scene and thereby preserve immersion. It consists of three stages: First, the object of interest is reconstructed from images and corresponding camera poses recorded with the VR headset, or alternatively a retrieval model finds a fitting mesh from the ShapeNet dataset. Second, a style transfer technique adapts the mesh to the VR game scene in order to preserve consistent immersion. Third, the stylised mesh is superimposed on the real object in real time to ensure interactivity even if the real object is moved. Our pipeline serves as proof of concept for style-aware AV embeddings.
Johannes Hoster, Dennis Ritter, Kristian Hildebrand
VR1