/en/tags/super-resolution/Recent content in Super Resolution on Mi&Bee BlogHugo -- gohugo.ioen蓝宝石的傻话Sat, 20 Jun 2026 10:00:00 +0800/en/posts/physical-world/image-interpolation-methods/Mon, 08 Jun 2026 10:00:00 +0800/en/posts/physical-world/image-interpolation-methods/<h2 id="why-interpolation-matters">Why Interpolation Matters</h2> <p>Imagine you have a low-resolution photo and want to print it larger. Between every two pixels in the original image is now a &ldquo;blank space&rdquo; — where do the new pixels come from?</p> <p>Interpolation is the solution: using known pixel values to estimate values at unknown positions. Image upscaling is essentially an interpolation problem.</p> <p>$$ \text{Upscaled Image} = \text{Interpolation Algorithm}(\text{Original Pixels}) $$</p> <p>The quality of interpolation directly affects the upscaled image. Too simple methods produce mosaic artifacts, while too complex methods may introduce ringing artifacts. Let&rsquo;s progress step by step, from the simplest nearest neighbor interpolation to the most commonly used bicubic interpolation.</p>/en/posts/physical-world/dl-super-resolution-srcnn-srgan/Sat, 20 Jun 2026 10:00:00 +0800/en/posts/physical-world/dl-super-resolution-srcnn-srgan/<h2 id="from-mathematical-models-to-data-driven-learning">From Mathematical Models to Data-Driven Learning</h2> <p>In super-resolution tasks, traditional methods rely on carefully designed mathematical models—interpolation algorithms, sparse representation, prior constraints, and so on. But deep learning brought a paradigm shift: directly learning the mapping from degraded space to clear space from massive paired low-resolution (LR) and high-resolution (HR) image data.</p> <p>The core idea is simple: train a neural network $F_{\theta}$ that can map low-resolution images to high-resolution images:</p>