DepthForge fuses frozen DINOv2 or EVA02 visual features with frozen Depth Anything V2 depth features via depth-aware learnable tokens and a refinement decoder to improve domain-generalized semantic segmentation.
Em-trans: Edge-aware multi- modal transformer for rgb-d salient object detection
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
-
Stronger, Steadier & Superior: Geometric Consistency in Depth VFM Forges Domain Generalized Semantic Segmentation
DepthForge fuses frozen DINOv2 or EVA02 visual features with frozen Depth Anything V2 depth features via depth-aware learnable tokens and a refinement decoder to improve domain-generalized semantic segmentation.