Related papers: Generative Preprocessing for Image Compression wit…

We propose a method to distill a complex multistep diffusion model into a single-step conditional GAN student model, dramatically accelerating inference, while preserving image quality. Our approach interprets diffusion distillation as a…

Dataset distillation aims to compress a dataset into a much smaller one so that a model trained on the distilled dataset achieves high accuracy. Current methods frame this as maximizing the distilled classification accuracy for a budget of…

Recent approaches have shown promises distilling diffusion models into efficient one-step generators. Among them, Distribution Matching Distillation (DMD) produces one-step generators that match their teacher in distribution, without…

Diffusion-based image super-resolution (SR) methods have shown promise in reconstructing high-resolution images with fine details from low-resolution counterparts. However, these approaches typically require tens or even hundreds of…

Recently, learned image compression schemes have achieved remarkable improvements in image fidelity (e.g., PSNR and MS-SSIM) compared to conventional hybrid image coding ones due to their high-efficiency non-linear transform, end-to-end…

We present a simple but effective training-free approach for text-driven image-to-image translation based on a pretrained text-to-image diffusion model. Our goal is to generate an image that aligns with the target task while preserving the…

Conditional image generation models have achieved remarkable results by leveraging text-based control to generate customized images. However, the high resource demands of these models and the scarcity of well-annotated data have hindered…

Learning generative models directly from corrupted observations is a long standing challenge across natural and scientific domains. We introduce Restoration Score Distillation (RSD), a unified framework for learning high fidelity, one step…

Image denoising aims to remove noise while preserving structural details and perceptual realism, yet distortion-driven methods often produce over-smoothed reconstructions, especially under strong noise and distribution shift. This paper…

Denoising diffusion models achieved impressive results on several image generation tasks often outperforming GAN based models. Recently, the generative capabilities of diffusion models have been employed for perceptual image compression,…

Diffusion models have achieved remarkable progress in the field of image generation due to their outstanding capabilities. However, these models require substantial computing resources because of the multi-step denoising process during…

Dataset distillation has emerged as an effective strategy, significantly reducing training costs and facilitating more efficient model deployment. Recent advances have leveraged generative models to distill datasets by capturing the…

While diffusion models can learn complex distributions, sampling requires a computationally expensive iterative process. Existing distillation methods enable efficient sampling, but have notable limitations, such as performance degradation…

We present the first text-based image editing approach for object parts based on pre-trained diffusion models. Diffusion-based image editing approaches capitalized on the deep understanding of diffusion models of image semantics to perform…

The slow inference process of image diffusion models significantly degrades interactive user experiences. To address this, we introduce Diffusion Preview, a novel paradigm employing rapid, low-step sampling to generate preliminary outputs…

Recently, diffusion models have shown remarkable results in image synthesis by gradually removing noise and amplifying signals. Although the simple generative process surprisingly works well, is this the best way to generate image data? For…

The performance of pre-trained masked diffusion models is often constrained by their sampling procedure, which makes decisions irreversible and struggles in low-step generation regimes. We introduce a novel sampling algorithm that works…

We present a generative method for texture filtering, which exhibits surprisingly good performance and generalizability. Our core idea is to empower texture filtering by taking full advantage of the strong learned image prior of pre-trained…

Distribution matching distillation (DMD) facilitates few-step image generation by aligning a distilled student with a reference multi-step teacher. In practice, however, optimizing DMD can reduce sample diversity in few-step synthesis, and…

Perceptual image super-resolution (SR) methods restore degraded images and produce sharp outputs. In practice, those outputs are usually recompressed for storage and transmission. Ignoring recompression is suboptimal as the downstream codec…