AI RESEARCH
GeomPrompt: Geometric Prompt Learning for RGB-D Semantic Segmentation Under Missing and Degraded Depth
arXiv CS.CV
•
ArXi:2604.11585v1 Announce Type: new Multimodal perception systems for robotics and embodied AI often assume reliable RGB-D sensing, but in practice, depth is frequently missing, noisy, or corrupted. We thus present GeomPrompt, a lightweight cross-modal adaptation module that synthesizes a task-driven geometric prompt from RGB alone for the fourth channel of a frozen RGB-D semantic segmentation model, without depth supervision. We further