Performing super-resolution of a depth image using the guidance from an RGB image is a problem that concerns several fields, such as robotics, medical imaging, and remote sensing. While deep learning methods have achieved good results in this problem, recent work highlighted the value of combining modern methods with more formal frameworks. In this work, we propose a novel approach which combines guided anisotropic diffusion with a deep convolutional network and advances the state of the art for guided depth super-resolution. The edge transferring/enhancing properties of the diffusion are boosted by the contextual reasoning capabilities of modern networks, and a strict adjustment step guarantees perfect adherence to the source image. We achieve unprecedented results in three commonly used benchmarks for guided depth super-resolution. The performance gain compared to other methods is the largest at larger scales, such as x32 scaling. Code (https://github.com/prs-eth/Diffusion-Super-Resolution) for the proposed method is available to promote reproducibility of our results.

翻译：利用RGB图像引导完成深度图像的超分辨率是机器人、医学成像及遥感等多个领域共同关注的问题。尽管深度学习方法在该问题上已取得良好成效，但近期研究强调了将现代方法与更规范框架相结合的价值。本研究提出一种新方法，将引导各向异性扩散与深度卷积网络相结合，推动了引导深度超分辨率技术的当前最优水平。扩散过程的边缘传递/增强特性通过现代网络的上下文推理能力得到强化，严格的自适应步骤确保了与源图像的完美一致性。我们在三个常用引导深度超分辨率基准测试中取得了前所未有的结果。相较于其他方法，性能提升在更大尺度（如×32放大因子）上最为显著。为促进结果可复现性，本研究方法代码（https://github.com/prs-eth/Diffusion-Super-Resolution）已公开。