用拉普拉斯金字塔提升热成像超分辨率，轻量高效且保细节。
LapGSR: Laplacian Reconstructive Network for Guided Thermal Super-Resolution
- 基于拉普拉斯金字塔提取RGB图像边缘信息，指导热成像超分。
- 参数量远低于当前最优模型，在两个跨域数据集上表现优异。
- 适合资源受限场景的多模态图像增强，如机器人视觉、自动驾驶。
近年来，多模态数据融合在机器人、手势识别和自主导航等领域受到广泛关注。由于高质量视觉传感器成本高，消费级设备生成的图像分辨率较低，研究者尝试将RGB彩色图像与热成像等非视觉数据融合以提升分辨率。现有方法常依赖参数量达数百万的密集模型，计算开销大，主要源于复杂架构。本文提出LapGSR，一种轻量级、多模态生成模型，结合拉普拉斯图像金字塔实现引导式热成像超分辨率。该方法利用拉普拉斯金字塔从RGB图像中提取关键边缘信息，从而在模型高层绕过复杂的特征图计算，并采用像素级与对抗性损失联合优化。LapGSR在保留图像空间与结构细节的同时，显著减少参数量，优于当前主流模型，在跨域数据集ULB17-VT与VGTSR上均取得优异表现。
原文摘要 · Abstract (English)
In the last few years, the fusion of multi-modal data has been widely studied for various applications such as robotics, gesture recognition, and autonomous navigation. Indeed, high-quality visual sensors are expensive, and consumer-grade sensors produce low-resolution images. Researchers have developed methods to combine RGB color images with non-visual data, such as thermal, to overcome this limitation to improve resolution. Fusing multiple modalities to produce visually appealing, high-resolution images often requires dense models with millions of parameters and a heavy computational load, which is commonly attributed to the intricate architecture of the model. We propose LapGSR, a multimodal, lightweight, generative model incorporating Laplacian image pyramids for guided thermal super-resolution. This approach uses a Laplacian Pyramid on RGB color images to extract vital edge information, which is then used to bypass heavy feature map computation in the higher layers of the model in tandem with a combined pixel and adversarial loss. LapGSR preserves the spatial and structural details of the image while also being efficient and compact. This results in a model with significantly fewer parameters than other SOTA models while demonstrating excellent results on two cross-domain datasets viz. ULB17-VT and VGTSR datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。