GeomPrompt learns a task-driven geometric prompt from RGB alone to substitute for missing or degraded depth in frozen RGB-D semantic segmentation models, yielding up to +6.1 mIoU gains on SUN RGB-D while being faster than monocular depth estimators.
Efficient attention vision trans- formers for monocular depth estimation on resource-limited hardware.Scientific Reports, 15(1):24001
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GeomPrompt: Geometric Prompt Learning for RGB-D Semantic Segmentation Under Missing and Degraded Depth
GeomPrompt learns a task-driven geometric prompt from RGB alone to substitute for missing or degraded depth in frozen RGB-D semantic segmentation models, yielding up to +6.1 mIoU gains on SUN RGB-D while being faster than monocular depth estimators.