LoCoVSR：用于视频超分辨率的局部上下文扩散后验采样
LoCoVSR: Local Context Diffusion Posterior Sampling for Video Super-Resolution
浏览论文内容
中文总结 AI 辅助
LoCoVSR提出一种基于像素空间扩散后验采样与局部时空上下文学习的视频超分辨率框架，通过局部窗口和共享噪声轨迹实现长视频高效并行推理，避免光流估计和潜在空间信息损失，在VFHQ数据集上取得有竞争力的结果。
中文摘要 AI 辅助
视频超分辨率（VSR）是一个不适定的逆问题，旨在从有噪声的低分辨率（LR）视频重建高分辨率（HR）视频。我们提出了LoCoVSR，一个基于扩散的VSR框架，利用像素空间去噪扩散概率模型。LoCoVSR将扩散后验采样技术与时空上下文学习相结合，以移动平均形式运行。使用相邻LR帧的局部窗口来恢复每个中心帧，同时对所有帧应用共享噪声轨迹。局部窗口化使得能够处理长视频而不受长度限制，支持并行推理，并防止递归处理中可能出现的误差累积。与先前方法不同，LoCoVSR提供了一种简单但非常有效的VSR解决方案，避免了显式光流估计或由潜在空间处理引起的信息损失。在VFHQ人脸数据集上训练，LoCoVSR实现了准确、时间一致且高质量的上采样，与近期基于扩散的VSR方法相比具有竞争力的结果。
英文摘要
Video super-resolution (VSR) is an ill-posed inverse problem that aims to reconstruct a high-resolution (HR) video from a noisy, low-resolution (LR) version of it. We present LoCoVSR, a diffusion-based VSR framework that leverages pixel-space denoising diffusion probabilistic models. LoCoVSR integrates the Diffusion Posterior Sampling technique with spatio-temporal context learning, operating in a moving-average form. A localized window of adjacent LR frames is used for recovering each center frame, while applying a shared noise trajectory across all frames. The localized windowing enables processing of long videos without length limitations, supports parallel inference, and prevents error accumulation that may occur in recursive processing. Unlike prior methods, LoCoVSR offers a simple yet very effective VSR solution, avoiding explicit optical flow estimation, or information loss caused by latent space processing. Trained on the VFHQ face dataset, LoCoVSR achieves accurate, temporally consistent and high-quality upscaling with competitive results against recent diffusion-based VSR approaches.
发表机构
- Technion - Israel Institute of Technology（以色列理工学院）
机构由 AI 辅助整理，请以论文原文为准。
