中文
相关论文

相关论文: RealisVSR: Detail-enhanced Diffusion for Real-Worl…

200 篇论文

Portrait pictures, which typically feature both human subjects and natural backgrounds, are one of the most prevalent forms of photography on social media. Existing image super-resolution (ISR) techniques generally focus either on generic…

计算机视觉与模式识别 · 计算机科学 2025-10-14 Renjie Li , Zihao Zhu , Xiaoyu Wang , Zhengzhong Tu

Recently, diffusion model-based inverse problem solvers (DIS) have emerged as state-of-the-art approaches for addressing inverse problems, including image super-resolution, deblurring, inpainting, etc. However, their application to video…

计算机视觉与模式识别 · 计算机科学 2025-02-28 Taesung Kwon , Jong Chul Ye

Visual diffusion models achieve remarkable progress, yet they are typically trained at limited resolutions due to the lack of high-resolution data and constrained computation resources, hampering their ability to generate high-fidelity…

计算机视觉与模式识别 · 计算机科学 2025-08-22 Haonan Qiu , Ning Yu , Ziqi Huang , Paul Debevec , Ziwei Liu

Recent advances in video generation have made it possible to produce visually compelling videos, with wide-ranging applications in content creation, entertainment, and virtual reality. However, most existing diffusion transformer based…

计算机视觉与模式识别 · 计算机科学 2025-10-22 Teng Hu , Jiangning Zhang , Zihan Su , Ran Yi

Text-to-video diffusion models have advanced video generation significantly. However, customizing these models to generate videos with tailored motions presents a substantial challenge. In specific, they encounter hurdles in (a) accurately…

计算机视觉与模式识别 · 计算机科学 2023-12-05 Hyeonho Jeong , Geon Yeong Park , Jong Chul Ye

Real-world image super-resolution (Real SR) aims to generate high-fidelity, detail-rich high-resolution (HR) images from low-resolution (LR) counterparts. Existing Real SR methods primarily focus on generating details from the LR RGB…

图像与视频处理 · 电气工程与系统科学 2024-11-22 Long Peng , Wenbo Li , Jiaming Guo , Xin Di , Haoze Sun , Yong Li , Renjing Pei , Yang Wang , Yang Cao , Zheng-Jun Zha

Conventional production workflow of high-precision mesh assets necessitates a cumbersome and laborious process of manual sculpting by specialized 3D artists/modelers. The recent years have witnessed remarkable advances in AI-empowered 3D…

计算机视觉与模式识别 · 计算机科学 2026-02-03 Qijian Zhang , Xiaozheng Jian , Xuan Zhang , Wenping Wang , Junhui Hou

Real-world image super-resolution is a critical image processing task, where two key evaluation criteria are the fidelity to the original image and the visual realness of the generated results. Although existing methods based on diffusion…

计算机视觉与模式识别 · 计算机科学 2025-03-20 Runyi Li , Bin Chen , Jian Zhang , Radu Timofte

Compressed video super-resolution (VSR) aims to restore high-resolution frames from compressed low-resolution counterparts. Most recent VSR approaches often enhance an input frame by borrowing relevant textures from neighboring video…

计算机视觉与模式识别 · 计算机科学 2022-08-08 Zhongwei Qiu , Huan Yang , Jianlong Fu , Dongmei Fu

Diffusion models have demonstrated remarkable performance in image and video synthesis. However, scaling them to high-resolution inputs is challenging and requires restructuring the diffusion pipeline into multiple independent components,…

计算机视觉与模式识别 · 计算机科学 2024-06-13 Ivan Skorokhodov , Willi Menapace , Aliaksandr Siarohin , Sergey Tulyakov

In this work, we rethink the approach to video super-resolution by introducing a method based on the Diffusion Posterior Sampling framework, combined with an unconditional video diffusion transformer operating in latent space. The video…

计算机视觉与模式识别 · 计算机科学 2025-11-05 Zhihao Zhan , Wang Pang , Xiang Zhu , Yechao Bai

Recent advances in diffusion-based real-world image super-resolution (Real-ISR) have demonstrated remarkable perceptual quality, yet the balance between fidelity and controllability remains a problem: multi-step diffusion-based methods…

计算机视觉与模式识别 · 计算机科学 2025-12-01 Yushun Fang , Yuxiang Chen , Shibo Yin , Qiang Hu , Jiangchao Yao , Ya Zhang , Xiaoyun Zhang , Yanfeng Wang

Although recent research applying text-to-image (T2I) diffusion models to real-world super-resolution (SR) has achieved remarkable progress, the misalignment of their targets leads to a suboptimal trade-off between inference speed and…

计算机视觉与模式识别 · 计算机科学 2026-02-12 Yan Wang , Shijie Zhao , Kexin Zhang , Junlin Li , Li Zhang

Video super-resolution (VSR) aims to estimate a high-resolution (HR) frame from a low-resolution (LR) frames. The key challenge for VSR lies in the effective exploitation of spatial correlation in an intra-frame and temporal dependency…

计算机视觉与模式识别 · 计算机科学 2021-06-15 Young-Ju Choi , Young-Woon Lee , Byung-Gyu Kim

Deep denoising models require extensive real-world training data, which is challenging to acquire. Current noise synthesis techniques struggle to accurately model complex noise distributions. We propose a novel Realistic Noise Synthesis…

计算机视觉与模式识别 · 计算机科学 2025-01-03 Qi Wu , Mingyan Han , Ting Jiang , Chengzhi Jiang , Jinting Luo , Man Jiang , Haoqiang Fan , Shuaicheng Liu

Video super-resolution (VSR) has become one of the most critical problems in video processing. In the deep learning literature, recent works have shown the benefits of using adversarial-based and perceptual losses to improve the performance…

计算机视觉与模式识别 · 计算机科学 2019-06-26 Alice Lucas , Santiago Lopez Tapia , Rafael Molina , Aggelos K. Katsaggelos

As deep convolutional neural networks (DNNs) are widely used in various fields of computer vision, leveraging the overfitting ability of the DNN to achieve video resolution upscaling has become a new trend in the modern video delivery…

计算机视觉与模式识别 · 计算机科学 2023-06-21 Gen Li , Jie Ji , Minghai Qin , Wei Niu , Bin Ren , Fatemeh Afghah , Linke Guo , Xiaolong Ma

Real-SR endeavors to produce high-resolution images with rich details while mitigating the impact of multiple degradation factors. Although existing methods have achieved impressive achievements in detail recovery, they still fall short…

图像与视频处理 · 电气工程与系统科学 2024-05-14 Long Peng , Yang Cao , Renjing Pei , Wenbo Li , Jiaming Guo , Xueyang Fu , Yang Wang , Zheng-Jun Zha

3D Gaussian Splatting (3DGS) enables high-quality novel view synthesis, motivating interest in generating higher-resolution renders than those available during training. A natural strategy is to apply super-resolution (SR) to low-resolution…

计算机视觉与模式识别 · 计算机科学 2026-04-01 Pranav Asthana , Alex Hanson , Allen Tu , Tom Goldstein , Matthias Zwicker , Amitabh Varshney

Deep Video Quality Assessment (VQA) methods have shown impressive high-performance capabilities. Notably, no-reference (NR) VQA methods play a vital role in situations where obtaining reference videos is restricted or not feasible.…

图像与视频处理 · 电气工程与系统科学 2024-07-31 Xiaoheng Tan , Jiabin Zhang , Yuhui Quan , Jing Li , Yajing Wu , Zilin Bian