中文
相关论文

相关论文: MoEDiff-SR: Mixture of Experts-Guided Diffusion Mo…

200 篇论文

Super Resolution (SR) plays a critical role in computer vision, particularly in medical imaging, where hardware and acquisition time constraints often result in low spatial and temporal resolution. While diffusion models have been applied…

图像与视频处理 · 电气工程与系统科学 2024-11-01 Vishal Dubey

Despite the proven significance of hyperspectral images (HSIs) in performing various computer vision tasks, its potential is adversely affected by the low-resolution (LR) property in the spatial domain, resulting from multiple physical…

计算机视觉与模式识别 · 计算机科学 2023-06-22 Chanyue Wu , Dong Wang , Hanyu Mao , Ying Li

Despite the significant progress in image denoising, it is still challenging to restore fine-scale details while removing noise, especially in extremely low-light environments. Leveraging near-infrared (NIR) images to assist visible RGB…

计算机视觉与模式识别 · 计算机科学 2025-03-11 Rongjian Xu , Zhilu Zhang , Renlong Wu , Wangmeng Zuo

As the deep learning revolution marches on, masked modeling has emerged as a distinctive approach that involves predicting parts of the original data that are proportionally masked during training, and has demonstrated exceptional…

图像与视频处理 · 电气工程与系统科学 2025-06-25 Qinrong Cai , Yu Guan , Zhibo Chen , Dong Liang , Qiuyun Fan , Qiegen Liu

Accurate brain tumor diagnosis relies on the assessment of multiple Magnetic Resonance Imaging (MRI) sequences. However, in clinical practice, the acquisition of certain sequences may be affected by factors like motion artifacts or contrast…

图像与视频处理 · 电气工程与系统科学 2025-05-30 Moinak Bhattacharya , Saumya Gupta , Annie Singh , Chao Chen , Gagandeep Singh , Prateek Prasanna

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

Background: High-resolution MRI is critical for diagnosis, but long acquisition times limit clinical use. Super-resolution (SR) can enhance resolution post-scan, yet existing deep learning methods face fidelity-efficiency trade-offs.…

Volumetric biomedical microscopy has the potential to increase the diagnostic information extracted from clinical tissue specimens and improve the diagnostic accuracy of both human pathologists and computational pathology models.…

图像与视频处理 · 电气工程与系统科学 2024-04-16 Cheng Jiang , Alexander Gedeon , Yiwei Lyu , Eric Landgraf , Yufeng Zhang , Xinhai Hou , Akhil Kondepudi , Asadur Chowdury , Honglak Lee , Todd Hollon

Diffusion models (DMs) excel in image generation but suffer from slow inference and training-inference discrepancies. Although gradient-based solvers for DMs accelerate denoising inference, they often lack theoretical foundations in…

计算机视觉与模式识别 · 计算机科学 2026-02-04 Shigui Li , Wei Chen , Delu Zeng

Ultrasound imaging, despite its widespread use in medicine, often suffers from various sources of noise and artifacts that impact the signal-to-noise ratio and overall image quality. Enhancing ultrasound images requires a delicate balance…

计算机视觉与模式识别 · 计算机科学 2024-09-18 Yuxin Zhang , Clément Huneau , Jérôme Idier , Diana Mateus

Diffusion-based stylization has advanced significantly, yet existing methods are limited to color-driven transformations, neglecting complex semantics and material details. We introduce StyleExpert, a semantic-aware framework based on the…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Shihao Zhu , Ziheng Ouyang , Yijia Kang , Qilong Wang , Mi Zhou , Bo Li , Ming-Ming Cheng , Qibin Hou

Reconstructing visual stimuli from functional Magnetic Resonance Imaging fMRI enables fine-grained retrieval of brain activity. However, the accurate reconstruction of diverse details, including structure, background, texture, color, and…

神经与进化计算 · 计算机科学 2025-01-09 Haoyu Li , Hao Wu , Badong Chen

Recent NeRF methods on large-scale scenes have underlined the importance of scene decomposition for scalable NeRFs. Although achieving reasonable scalability, there are several critical problems remaining unexplored, i.e., learnable…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Zhenxing Mi , Ping Yin , Xue Xiao , Dan Xu

All-in-one image restoration is challenging because different degradation types, such as haze, blur, noise, and low-light, impose diverse requirements on restoration strategies, making it difficult for a single model to handle them…

计算机视觉与模式识别 · 计算机科学 2026-03-04 Lingshun Kong , Jiawei Zhang , Zhengpeng Duan , Xiaohe Wu , Yueqi Yang , Xiaotao Wang , Dongqing Zou , Lei Lei , Jinshan Pan

Denoising diffusion models (DDM) have gained recent traction in medical image translation given improved training stability over adversarial models. DDMs learn a multi-step denoising transformation to progressively map random Gaussian-noise…

图像与视频处理 · 电气工程与系统科学 2024-05-14 Fuat Arslan , Bilal Kabas , Onat Dalmaz , Muzaffer Ozbey , Tolga Çukur

Multimodal medical image fusion is a crucial task that combines complementary information from different imaging modalities into a unified representation, thereby enhancing diagnostic accuracy and treatment planning. While deep learning…

图像与视频处理 · 电气工程与系统科学 2024-11-19 Meng Zhou , Yuxuan Zhang , Xiaolan Xu , Jiayi Wang , Farzad Khalvati

Magnetic resonance imaging (MRI) can present multi-contrast images of the same anatomical structures, enabling multi-contrast super-resolution (SR) techniques. Compared with SR reconstruction using a single-contrast, multi-contrast SR…

图像与视频处理 · 电气工程与系统科学 2022-03-29 Guangyuan Li , Jun Lv , Yapeng Tian , Qi Dou , Chengyan Wang , Chenliang Xu , Jing Qin

Diffusion models have achieved impressive performance on multi-focus image fusion (MFIF). However, a key challenge in applying diffusion models to the ill-posed MFIF problem is that defocus blur can make common symmetric geometric…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Bo Li , Tingting Bao , Lingling Zhang , Weiping Fu , Yaxian Wang , Jun Liu

By integrating the generative strengths of diffusion models with the representation capabilities of frequency-domain attention, DFAM effectively enhances reconstruction performance under low-SNR condi-tions. Experimental results demonstrate…

医学物理 · 物理学 2025-07-25 Xin Xie , Yu Guan , Zhuoxu Cui , Dong Liang , Qiegen Liu

Color-guided depth map super-resolution (CDSR) improve the spatial resolution of a low-quality depth map with the corresponding high-quality color map, benefiting various applications such as 3D reconstruction, virtual reality, and…

计算机视觉与模式识别 · 计算机科学 2023-11-17 Yuan Shi , Bin Xia , Rui Zhu , Qingmin Liao , Wenming Yang