A self-supervised frame-reconstruction objective trains RepGen to turn a three-channel EvRep into a five-channel EvRepSL that boosts downstream event-based vision performance across cameras.
A 128 ×128 120 db 15 µs latency asynchronous temporal contrast vision sensor,
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
EvRepSL: Event-Stream Representation via Self-Supervised Learning for Event-Based Vision
A self-supervised frame-reconstruction objective trains RepGen to turn a three-channel EvRep into a five-channel EvRepSL that boosts downstream event-based vision performance across cameras.