中文
相关论文

相关论文: SRSR: Enhancing Semantic Accuracy in Real-World Im…

200 篇论文

Image super-resolution (SR) aims to reconstruct high resolution images with both high perceptual quality and low distortion, but is fundamentally limited by the perception-distortion trade-off. GAN-based SR methods reduce distortion but…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Dan Wang , Haiyan Sun , Shan Du , Z. Jane Wang , Zhaochong An , Serge Belongie , Xinrui Cui

The rich textual information of large vision-language models (VLMs) combined with the powerful generative prior of pre-trained text-to-image (T2I) diffusion models has achieved impressive performance in single-image super-resolution (SISR).…

计算机视觉与模式识别 · 计算机科学 2025-08-25 Haodong He , Yancheng Bai , Rui Lan , Xu Duan , Lei Sun , Xiangxiang Chu , Gui-Song Xia

Hyperspectral images super-resolution aims to improve the spatial resolution, yet its performance is often limited at high-resolution ratios. The recent adoption of high-resolution reference images for super-resolution is driven by the poor…

计算机视觉与模式识别 · 计算机科学 2026-01-06 Yingkai Zhang , Zeqiang Lai , Tao Zhang , Ying Fu , Chenghu Zhou

Real-world image super-resolution (Real-ISR) has achieved a remarkable leap by leveraging large-scale text-to-image models, enabling realistic image restoration from given recognition textual prompts. However, these methods sometimes fail…

计算机视觉与模式识别 · 计算机科学 2024-12-05 Jiahua Xiao , Jiawei Zhang , Dongqing Zou , Xiaodan Zhang , Jimmy Ren , Xing Wei

While recent advancements in Image Super-Resolution (SR) using diffusion models have shown promise in improving overall image quality, their application to scene text images has revealed limitations. These models often struggle with…

计算机视觉与模式识别 · 计算机科学 2025-05-30 Keren Ye , Ignacio Garcia Dorado , Michalis Raptis , Mauricio Delbracio , Irene Zhu , Peyman Milanfar , Hossein Talebi

Image Super-Resolution (SR) aims to reconstruct high-resolution images from degraded low-resolution inputs. While diffusion-based SR methods offer powerful generative capabilities, their performance heavily depends on how semantic priors…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Lei Jiang , Xin Liu , Xinze Tong , Zhiliang Li , Jie Liu , Jie Tang , Gangshan Wu

Existing super-resolution (SR) models primarily focus on restoring local texture details, often neglecting the global semantic information within the scene. This oversight can lead to the omission of crucial semantic details or the…

计算机视觉与模式识别 · 计算机科学 2023-12-22 Haoze Sun , Wenbo Li , Jianzhuang Liu , Haoyu Chen , Renjing Pei , Xueyi Zou , Youliang Yan , Yujiu Yang

Deep neural networks have greatly promoted the performance of single image super-resolution (SISR). Conventional methods still resort to restoring the single high-resolution (HR) solution only based on the input of image modality. However,…

计算机视觉与模式识别 · 计算机科学 2022-07-15 Chenxi Ma , Bo Yan , Qing Lin , Weimin Tan , Siming Chen

Speech super-resolution (SR) reconstructs high-fidelity wideband speech from low-resolution inputs-a task that necessitates reconciling global harmonic coherence with local transient sharpness. While diffusion-based generative models yield…

声音 · 计算机科学 2026-01-01 Jiajun Yuan , Xiaochen Wang , Yuhang Xiao , Yulin Wu , Chenhao Hu , Xueyang Lv

Diffusion models have recently achieved significant success in various image manipulation tasks, including image super-resolution and perceptual quality enhancement. Pretrained text-to-image models, such as Stable Diffusion, have exhibited…

计算机视觉与模式识别 · 计算机科学 2025-10-16 Sanchar Palit , Subhasis Chaudhuri , Biplab Banerjee

The introduction of generative models has significantly advanced image super-resolution (SR) in handling real-world degradations. However, they often incur fidelity-related issues, particularly distorting textual structures. In this paper,…

计算机视觉与模式识别 · 计算机科学 2025-06-06 Qiming Hu , Linlong Fan , Yiyan Luo , Yuhang Yu , Xiaojie Guo , Qingnan Fan

Restoring low-resolution text images presents a significant challenge, as it requires maintaining both the fidelity and stylistic realism of the text in restored images. Existing text image restoration methods often fall short in hard…

计算机视觉与模式识别 · 计算机科学 2025-06-17 Chenglu Pan , Xiaogang Xu , Ganggui Ding , Yunke Zhang , Wenbo Li , Jiarong Xu , Qingbiao Wu

Existing real-world super-resolution (RSR) methods based on generative priors have achieved remarkable progress in producing high-quality and globally consistent reconstructions. However, they often struggle to recover fine-grained details…

计算机视觉与模式识别 · 计算机科学 2026-03-26 Zixin Guo , Kai Zhao , Luyan Zhang

Diffusion prior-based methods have shown impressive results in real-world image super-resolution (SR). However, most existing methods entangle pixel-level and semantic-level SR objectives in the training process, struggling to balance…

计算机视觉与模式识别 · 计算机科学 2025-04-04 Lingchen Sun , Rongyuan Wu , Zhiyuan Ma , Shuaizheng Liu , Qiaosi Yi , Lei Zhang

Recent advances in self-supervised learning, predominantly studied in high-level visual tasks, have been explored in low-level image processing. This paper introduces a novel self-supervised constraint for single image super-resolution,…

计算机视觉与模式识别 · 计算机科学 2024-04-02 Gang Wu , Junjun Jiang , Kui Jiang , Xianming Liu

Scene text recognition has witnessed rapid development with the advance of convolutional neural networks. Nonetheless, most of the previous methods may not work well in recognizing text with low resolution which is often seen in natural…

计算机视觉与模式识别 · 计算机科学 2019-10-22 Wenjia Wang , Enze Xie , Peize Sun , Wenhai Wang , Lixun Tian , Chunhua Shen , Ping Luo

Convolutional Neural Networks (CNNs) have significantly advanced Image Super-Resolution (SR), yet most CNN-based methods rely solely on pixel-based transformations, often leading to artifacts and blurring, particularly under severe…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Bingwen Hu , Heng Liu , Zhedong Zheng , Ping Liu

Reference-based Super Resolution (RefSR) improves upon Single Image Super Resolution (SISR) by leveraging high-quality reference images to enhance texture fidelity and visual realism. However, a critical limitation of existing RefSR…

计算机视觉与模式识别 · 计算机科学 2026-05-28 Jiaqi Yan , Shuning Xu , Xiangyu Chen , Dell Zhang , Jiantao Zhou , Jie Tang , Gangshan Wu , Jie Liu

We present a novel approach to reference-based super-resolution (RefSR) with the focus on dual-camera super-resolution (DCSR), which utilizes reference images for high-quality and high-fidelity results. Our proposed method generalizes the…

计算机视觉与模式识别 · 计算机科学 2021-09-07 Tengfei Wang , Jiaxin Xie , Wenxiu Sun , Qiong Yan , Qifeng Chen

Super-resolution (SR), a classical inverse problem in computer vision, is inherently ill-posed, inducing a distribution of plausible solutions for every input. However, the desired result is not simply the expectation of this distribution,…

计算机视觉与模式识别 · 计算机科学 2025-04-28 Fengjia Zhang , Samrudhdhi B. Rangrej , Tristan Aumentado-Armstrong , Afsaneh Fazly , Alex Levinshtein
‹ 上一页 1 2 3 10 下一页 ›