中文
相关论文

相关论文: Fast Image Super-Resolution via Consistency Rectif…

200 篇论文

Diffusion-based image super-resolution (SR) has recently attracted significant attention by leveraging the expressive power of large pre-trained text-to-image diffusion models (DMs). A central practical challenge is resolving the trade-off…

图像与视频处理 · 电气工程与系统科学 2026-01-26 Maxence Noble , Gonzalo Iñaki Quintana , Benjamin Aubin , Clément Chadebec

Diffusion- and flow-based models have advanced Real-world Image Super-Resolution (Real-ISR), but their multi-step sampling makes inference slow and hard to deploy. One-step distillation alleviates the cost, yet often degrades restoration…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Ruiqing Wang , Kai Zhang , Yuanzhi Zhu , Hanshu Yan , Shilin Lu , Jian Yang

Super-resolution suffers from an innate ill-posed problem that a single low-resolution (LR) image can be from multiple high-resolution (HR) images. Recent studies on the flow-based algorithm solve this ill-posedness by learning the…

计算机视觉与模式识别 · 计算机科学 2022-04-22 Ki-Ung Song , Dongseok Shim , Kang-wook Kim , Jae-young Lee , Younggeun Kim

Recent advances in diffusion and flow-based generative models have demonstrated remarkable success in image restoration tasks, achieving superior perceptual quality compared to traditional deep learning approaches. However, these methods…

计算机视觉与模式识别 · 计算机科学 2026-03-20 Yuanzhi Zhu , Ruiqing Wang , Shilin Lu , Junnan Li , Hanshu Yan , Kai Zhang

While burst Low-Resolution (LR) images are useful for improving their Super Resolution (SR) image compared to a single LR image, prior burst SR methods are trained in a deterministic manner, which produces a blurry SR image. Since such…

计算机视觉与模式识别 · 计算机科学 2025-07-21 Kento Kawai , Takeru Oba , Kyotaro Tokoro , Kazutoshi Akita , Norimichi Ukita

Diffusion models (DMs) have significantly advanced the development of real-world image super-resolution (Real-ISR), but the computational cost of multi-step diffusion models limits their application. One-step diffusion models generate…

计算机视觉与模式识别 · 计算机科学 2025-02-13 Jianze Li , Jiezhang Cao , Yong Guo , Wenbo Li , Yulun Zhang

Recent advancements in diffusion models (DMs) have greatly advanced remote sensing image super-resolution (RSISR). However, their iterative sampling processes often result in slow inference speeds, limiting their application in real-time…

图像与视频处理 · 电气工程与系统科学 2025-03-26 Xiaohui Sun , Jiangwei Mo , Hanlin Wu , Jie Ma

Current diffusion-based super-resolution (SR) approaches achieve commendable performance at the cost of high inference overhead. Therefore, distillation techniques are utilized to accelerate the multi-step teacher model into one-step…

计算机视觉与模式识别 · 计算机科学 2025-11-10 Weiyi You , Mingyang Zhang , Leheng Zhang , Xingyu Zhou , Kexuan Shi , Shuhang Gu

Audio super-resolution aims to recover missing high-frequency details from bandwidth-limited low-resolution audio, thereby improving the naturalness and perceptual quality of the reconstructed signal. However, most existing methods directly…

声音 · 计算机科学 2026-04-13 Fei Liu , Yang Ai , Hui-Peng Du , Yu-Fei Shi , Zhen-Hua Ling

While deep learning-based super-resolution (SR) methods have shown impressive outcomes with synthetic degradation scenarios such as bicubic downsampling, they frequently struggle to perform well on real-world images that feature complex,…

计算机视觉与模式识别 · 计算机科学 2026-02-05 Hyeonjae Kim , Dongjin Kim , Eugene Jin , Tae Hyun Kim

We present a novel method for diffusion-guided frameworks for view-consistent super-resolution (SR) in neural rendering. Our approach leverages existing 2D SR models in conjunction with advanced techniques such as Variational Score…

计算机视觉与模式识别 · 计算机科学 2025-01-07 Shrey Vishen , Jatin Sarabu , Saurav Kumar , Chinmay Bharathulwar , Rithwick Lakshmanan , Vishnu Srinivas

While super-resolution (SR) methods based on diffusion models exhibit promising results, their practical application is hindered by the substantial number of required inference steps. Recent methods utilize degraded images in the initial…

计算机视觉与模式识别 · 计算机科学 2023-11-28 Yufei Wang , Wenhan Yang , Xinyuan Chen , Yaohui Wang , Lanqing Guo , Lap-Pui Chau , Ziwei Liu , Yu Qiao , Alex C. Kot , Bihan Wen

Diffusion-based image super-resolution (SR) methods are mainly limited by the low inference speed due to the requirements of hundreds or even thousands of sampling steps. Existing acceleration sampling techniques inevitably sacrifice…

计算机视觉与模式识别 · 计算机科学 2023-10-19 Zongsheng Yue , Jianyi Wang , Chen Change Loy

The generative priors of pre-trained latent diffusion models (DMs) have demonstrated great potential to enhance the visual quality of image super-resolution (SR) results. However, the noise sampling process in DMs introduces randomness in…

图像与视频处理 · 电气工程与系统科学 2024-09-26 Lingchen Sun , Rongyuan Wu , Jie Liang , Zhengqiang Zhang , Hongwei Yong , Lei Zhang

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…

计算机视觉与模式识别 · 计算机科学 2024-08-15 Xiao He , Huaao Tang , Zhijun Tu , Junchao Zhang , Kun Cheng , Hanting Chen , Yong Guo , Mingrui Zhu , Nannan Wang , Xinbo Gao , Jie Hu

Flow-based generative super-resolution (SR) models learn to produce a diverse set of feasible SR solutions, called the SR space. Diversity of SR solutions increases with the temperature ($\tau$) of latent variables, which introduces random…

计算机视觉与模式识别 · 计算机科学 2022-09-20 Cansu Korkmaz , A. Murat Tekalp , Zafer Dogan , Erkut Erdem , Aykut Erdem

High-resolution remote sensing images (RSIs) are crucial for Earth observation applications, yet acquiring them is often limited by sensor constraints and costs. In recent years, generative super-resolution (SR) methods, particularly…

计算机视觉与模式识别 · 计算机科学 2026-05-22 Jiangwei Mo , Xi Lu , Hanlin Wu

Pre-trained text-to-image diffusion models are increasingly applied to real-world image super-resolution (Real-ISR) task. Given the iterative refinement nature of diffusion models, most existing approaches are computationally expensive.…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Linwei Dong , Qingnan Fan , Yihong Guo , Zhonghao Wang , Qi Zhang , Jinwei Chen , Yawei Luo , Changqing Zou

Super-resolution (SR) aims to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts, often relying on effective downsampling to generate diverse and realistic training pairs. In this work, we propose a…

图像与视频处理 · 电气工程与系统科学 2025-03-18 Sohwi Kim , Tae-Kyun Kim

Reference-based Image Super-Resolution (RefSR) aims to restore a low-resolution (LR) image by utilizing the semantic and texture information from an additional reference high-resolution (reference HR) image. Existing diffusion-based RefSR…

计算机视觉与模式识别 · 计算机科学 2025-08-15 Zhenning Shi , Zizheng Yan , Yuhang Yu , Clara Xue , Jingyu Zhuang , Qi Zhang , Jinwei Chen , Tao Li , Qingnan Fan
‹ 上一页 1 2 3 10 下一页 ›