HP-UniIF: Hierarchical Prompt Learning for Unified Image Fusion
Read the original on arXiv Computer Vision →HP-UniIF is a unified vision framework that uses diffusion priors and a depth‑wise hierarchical conditional modulation strategy to support heterogeneous image fusion, visual restoration, and downstream perception tasks. The framework introduces task prompt modulation at bottleneck layers, a degradation prompt router at shallow layers, and an application prompt bank at decoding stages to decouple and adapt to different objectives. Experiments across multiple fusion tasks, degradations, and downstream applications show that HP‑UniIF achieves superior performance while maintaining visually faithful results and task‑relevant semantics.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.