A frame-event fusion framework with ANN and SNN branches achieves state-of-the-art semantic segmentation on DDD17-Seg, DSEC-Semantic and a new M3ED-Semantic subset, with a reported 65% energy reduction on DSEC-Semantic.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient Event-Based Semantic Segmentation via Exploiting Frame-Event Fusion: A Hybrid Neural Network Approach
A frame-event fusion framework with ANN and SNN branches achieves state-of-the-art semantic segmentation on DDD17-Seg, DSEC-Semantic and a new M3ED-Semantic subset, with a reported 65% energy reduction on DSEC-Semantic.