Detail View

3D Hand Sequence Recovery from Real Blurry Images and Event Stream
Citations

WEB OF SCIENCE

Citations

SCOPUS

Metadata Downloads

Title
3D Hand Sequence Recovery from Real Blurry Images and Event Stream
Issued Date
2024-10-01
Citation
Park, Joonkyu. (2024-10-01). 3D Hand Sequence Recovery from Real Blurry Images and Event Stream. European Conference on Computer Vision (poster), 343–359. doi: 10.1007/978-3-031-73202-7_20
Type
Conference Paper
ISBN
9783031732027
ISSN
0302-9743
Abstract
Although hands frequently exhibit motion blur due to their dynamic nature, existing approaches for 3D hand recovery often disregard the impact of motion blur in hand images. Blurry hand images contain hands from multiple time steps, lack precise hand location at a specific time step, and introduce temporal ambiguity, leading to multiple possible hand trajectories. To address this issue and in the absence of datasets with real blur, we introduce the EBH dataset, which provides 1) hand images with real motion blur and 2) event data for authentic representation of fast hand movements. In conjunction with our new dataset, we present EBHNet, a novel network capable of recovering 3D hands from diverse input combinations, including blurry hand images, events, or both. Here, the event stream enhances motion understanding in blurry hands, addressing temporal ambiguity. Recognizing that blurry hand images include not only single 3D hands at a time step but also multiple hands along their motion trajectories, we design EBHNet to generate 3D hand sequences in motion. Moreover, to enable our EBHNet to predict 3D hands at novel, unsupervised time steps using a single shared module, we employ a Transformer-based module, temporal splitter, into EBHNet. Our experiments show the superior performance of EBH and EBHNet, especially in handling blurry hand images, making them valuable in real-world applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
URI
http://hdl.handle.net/20.500.11750/57549
DOI
10.1007/978-3-031-73202-7_20
Publisher
European Computer Vision Association (ECVA)
Show Full Item Record

File Downloads

  • There are no files associated with this item.

공유

qrcode
공유하기

Related Researcher

문경식
Moon, Gyeongsik문경식

Department of Electrical Engineering and Computer Science

read more

Total Views & Downloads