# Multigrain-aware Semantic Prototype Scanning and Tri-Token Prompt Learning Embraced High-Order RWKV for Pan-Sharpening

arXiv: https://arxiv.org/abs/2604.14622 · HTML: https://mlsanity.com/paper/2604.14622/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 30 references that are in the map.
- First posted on arXiv 16 Apr 2026.

## Builds on (most cited first, 6 of 6)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures](https://mlsanity.com/paper/2403.02308/) (2024)
- [A Multi-Scale and Multi-Depth Convolutional Neural Network for Remote Sensing Imagery Pan-Sharpening](https://mlsanity.com/paper/1712.09809/) (2017)
- [Deep Gradient Projection Networks for Pan-sharpening](https://mlsanity.com/paper/2103.04584/) (2021)
- [PanFlowNet: A Flow-Based Deep Network for Pan-sharpening](https://mlsanity.com/paper/2305.07774/) (2023)
- [RAP-SR: RestorAtion Prior Enhancement in Diffusion Models for Realistic Image Super-Resolution](https://mlsanity.com/paper/2412.07149/) (2024)

## Abstract (arXiv)

In this work, we propose a Multigrain-aware Semantic Prototype Scanning paradigm for pan-sharpening, built upon a high-order RWKV architecture and a tri-token prompting mechanism derived from semantic clustering. Specifically, our method contains three key components: 1) Multigrain-aware Semantic Prototype Scanning. Although RWKV offers a efficient linear-complexity alternative to Transformers, its conventional bidirectional raster scanning is still semantic-agnostic and prone to positional bias. To address this issue, we introduce a semantic-driven scanning strategy that leverages locality-sensitive hashing to group semantically related regions and construct multi-grain semantic prototypes, enabling context-aware token reordering and more coherent global interaction. 2) Tri-token Prompt Learning. We design a tri-token prompting mechanism consisting of a global token, cluster-derived prototype tokens, and a learnable register token. The global and prototype tokens provide complementary semantic priors for RWKV modeling, while the register token helps suppress noisy and artifact-prone intermediate representations. 3) Invertible Q-Shift. To counteract spatial details, we apply center difference convolution on the value pathway to inject high-frequency information, and introduce an invertible multi-scale Q-shift operation for efficient and lossless feature transformation without parameter-heavy receptive field expansion. Experimental results demonstrate the superiority of our method.