TCDM: Effective Large-Factor Image Super-Resolution via Texture Consistency Diffusion

Recently, remote sensing super-resolution (SR) tasks have been widely studied and achieved remarkable performance. However, due to the complex texture and serious image degeneration, the conventional methods (e.g. CNN-based, GAN-based) cannot reconstruct high-resolution (HR) remote sensing images with a large SR factor (≥ ×8). In this paper, we model the large-factor super-resolution (LFSR) task as a referenced diffusion process and explore how to embed pixel-wise constraint into the popular diffusion model. Following this motivation, we propose the first diffusion-based LFSR method named texture consistency diffusion model (TCDM) for remote sensing images. Specifically, we build a novel conditional truncated noise generator (CTNG) in TCDM to simultaneously generate the expectation of posterior probability p ( x _t-1 | x _t ) and the truncated noise image. With the predicted truncated noise image, sampling an SR image using CTNG saves nearly 90% processing time compared to the naive diffusion model. Additionally, we design a new denoising process named texture consistency diffusion (TC-diffusion) to explicitly embed pixel-wise constraints into the LFSR diffusion model during the training stage. Universal experiments on five commonly used remote sensing datasets demonstrate that the proposed TCDM surpasses the latest SR methods by a large margin and reports new SOTA results on several evaluation metrics. Additionally, the proposed method demonstrates impressive visual quality on reconstructed remote sensing image texture and details.