Related papers: Towards Efficient Low-rate Image Compression with …
Aligning Diffusion models has achieved remarkable breakthroughs in generating high-quality, human preference-aligned images. Existing techniques, such as supervised fine-tuning (SFT) and DPO-style preference optimization, have become…
Optimizing video inference efficiency has become increasingly important with the growing demand for video analysis in various fields. Some existing methods achieve high efficiency by explicit discard of spatial or temporal information,…
In this work, we utilize the high-fidelity generation abilities of diffusion models to solve blind JPEG restoration at high compression levels. We propose an elegant modification of the forward stochastic differential equation of diffusion…
The class-conditional image generation based on diffusion models is renowned for generating high-quality and diverse images. However, most prior efforts focus on generating images for general categories, e.g., 1000 classes in ImageNet-1k. A…
Burst image super resolution (BISR) aims to construct a single high-resolution (HR) image by aggregating information from multiple low-resolution (LR) frames, relying on temporal redundancy and spatial coherence across the burst. While…
Diffusion models have marked a significant breakthrough in the synthesis of semantically coherent images. However, their extensive noise estimation networks and the iterative generation process limit their wider application, particularly on…
Deep MRI reconstruction is commonly performed with conditional models that de-alias undersampled acquisitions to recover images consistent with fully-sampled data. Since conditional models are trained with knowledge of the imaging operator,…
Oversmoothing remains a persistent problem when applying deep learning to off-axis quantitative phase imaging (QPI). End-to-end U-Nets favour low-frequency content and under-represent fine, diagnostic detail. We trace this issue to spectral…
Diffusion models are a new class of generative models, and have dramatically promoted image generation with unprecedented quality and diversity. Existing diffusion models mainly try to reconstruct input image from a corrupted one with a…
Diffusion models, known for their powerful generative capabilities, play a crucial role in addressing real-world super-resolution challenges. However, these models often focus on improving local textures while neglecting the impacts of…
Diffusion models have achieved remarkable success in high-fidelity image generation but remain computationally demanding due to their multi-step denoising process and large model sizes. Although prior work improves efficiency either by…
Text image super-resolution (Text-SR) requires more than visually plausible detail synthesis: slight errors in stroke topology may alter character identity and break readability. Existing methods improve text fidelity with stronger…
Recent learning-based lossless image compression methods encode an image in the unit of subimages and achieve comparable performances to conventional non-learning algorithms. However, these methods do not consider the performance drop in…
Existing fusion methods are tailored for high-quality images but struggle with degraded images captured under harsh circumstances, thus limiting the practical potential of image fusion. This work presents a \textbf{D}egradation and…
Popularized by their strong image generation performance, diffusion and related methods for generative modeling have found widespread success in visual media applications. In particular, diffusion methods have enabled new approaches to data…
There is a rapidly growing interest in controlling consistency across multiple generated images using diffusion models. Among various methods, recent works have found that simply manipulating attention modules by concatenating features from…
We propose in this paper an analytically new construct of a diffusion model whose drift and diffusion parameters yield an exponentially time-decaying Signal to Noise Ratio in the forward process. In reverse, the construct cleverly carries…
Due to storage and bandwidth limitations, videos transmitted over the Internet often exhibit low quality, characterized by low-resolution and compression artifacts. Although video super-resolution (VSR) is an efficient video enhancing…
Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step generators combine image-space reward optimization with…
Perceptual image compression has shown strong potential for producing visually appealing results at low bitrates, surpassing classical standards and pixel-wise distortion-oriented neural methods. However, existing methods typically improve…