A new pipeline for egocentric event-based 3D hand mesh reconstruction uses a hand segmentation module to suppress background events and outperforms prior methods on the synthetic N-HOT3D dataset.
In particular, our method improved the R-AUC by approximately 0.2 points compared to the baseline
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
EventEgoHands: Event-based Egocentric 3D Hand Mesh Reconstruction
A new pipeline for egocentric event-based 3D hand mesh reconstruction uses a hand segmentation module to suppress background events and outperforms prior methods on the synthetic N-HOT3D dataset.