FMF-SLAM extends DROID-SLAM with Fourier-domain attention and cross-modal knowledge distillation for RGB-depth fusion, reporting fewer tracking failures and lower average trajectory error on dark, dim, and fast-moving test sequences.
Attentive multimodal fusion for optical and scene flow,
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
unclear 1representative citing papers
citing papers explorer
-
Multimodal Fusion SLAM with Fourier Attention
FMF-SLAM extends DROID-SLAM with Fourier-domain attention and cross-modal knowledge distillation for RGB-depth fusion, reporting fewer tracking failures and lower average trajectory error on dark, dim, and fast-moving test sequences.