Researchers present VascuSR, an iterative anatomy-aware diffusion method for generative super-resolution of computed tomography (CT) images, addressing the problem that missing high-frequency content is not uniquely determined by low-resolution input and that visually plausible reconstructions may contain anatomical errors. The work targets recovery of sharp detail from severely downsampled CT observations.
Generative super-resolution (SR) can recover sharp detail in computed tomography (CT) images from severely downsampled observations, but the missing high-frequency content is not uniquely determined by the low-resolution input. Consequently, visually plausible reconstructions may contain anatomicall
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.