Projekte pro Jahr
Abstract
Diminished Reality (DR) propagates pixels from a keyframe to subsequent frames for real-time inpainting. Keyframe selection has a significant impact on the inpainting quality, but untrained users struggle to identify good keyframes. Automatic selection is not straightforward either, since no previous work has formalized or verified what determines a good keyframe. We propose a novel metric to select good keyframes to inpaint. We examine the heuristics adopted in existing DR inpainting approaches and derive multiple simple criteria measurable from SLAM. To combine these criteria, we empirically analyze their effect on the quality using a novel representative test dataset. Our results demonstrate that the combined metric selects RGBD keyframes leading to high-quality inpainting results more often than a baseline approach in both color and depth domains. Also, we confirmed that our approach has a better ranking ability of distinguishing good and bad keyframes. Compared to random selections, our metric selects keyframes that would lead to higher-quality and more stably converging inpainting results. We present three DR examples, automatic keyframe selection, user navigation, and marker hiding.
Originalsprache | englisch |
---|---|
Seiten (von - bis) | 1 |
Seitenumfang | 1 |
Fachzeitschrift | IEEE Transactions on Visualization and Computer Graphics |
DOIs | |
Publikationsstatus | Veröffentlicht - 23 Mai 2022 |
ASJC Scopus subject areas
- Software
- Signalverarbeitung
- Maschinelles Sehen und Mustererkennung
- Computergrafik und computergestütztes Design
Fingerprint
Untersuchen Sie die Forschungsthemen von „Good Keyframes to Inpaint“. Zusammen bilden sie einen einzigartigen Fingerprint.Projekte
- 1 Laufend
-
FWF - 3DDR - Dreidimensionale Diminished Reality in Echtzeit
1/01/21 → 31/12/24
Projekt: Forschungsprojekt
Aktivitäten
-
How Far Can We Go for Diminished Reality Without Neural Networks?
Shohei Mori (Redner/in)
21 Okt. 2022Aktivität: Vortrag oder Präsentation › Invited talk bei Konferenz oder Fachtagung › Science to science
-
Good Keyframes to Inpaint
Shohei Mori (Redner/in)
18 Okt. 2022Aktivität: Vortrag oder Präsentation › Vortrag bei Konferenz oder Fachtagung › Science to science
-
2022 IEEE International Symposium on Mixed and Augmented Reality
Shohei Mori (Teilnehmer/-in)
17 Okt. 2022 → 21 Okt. 2022Aktivität: Teilnahme an / Organisation von › Konferenz oder Fachtagung (Teilnahme an/Organisation von)