提出可处理8K视频的自适应光流模型，突破传统方法分辨率限制。
DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework
- 设计双金字塔架构，动态适应高分辨率输入
- 在8K分辨率下优于现有方法，训练仅用低分辨率数据
- 构建首个覆盖1K–8K的评测基准，推动高质量光流评估
光流估计对视频修复、动作识别等任务至关重要。随着视频分辨率提升至8K，现有光流方法因固定架构难以泛化到大尺寸输入，常通过降采样或分块处理，导致细节与全局信息丢失。且缺乏真实高分辨率评测基准，以往评估仅基于人工挑选样本进行定性分析。本文从两方面填补空白：提出DPFlow，一种可在仅用低分辨率数据训练的前提下，适配8K输入的自适应光流架构；并构建Kubric-NK，首个覆盖1K至8K分辨率的评测基准。高分辨率实验揭示了现有方法的真实泛化能力边界。大量实验表明，DPFlow在MPI-Sintel、KITTI 2015、Spring等高分辨率基准上达到领先性能。
原文摘要 · Abstract (English)
Optical flow estimation is essential for video processing tasks, such as restoration and action recognition. The quality of videos is constantly increasing, with current standards reaching 8K resolution. However, optical flow methods are usually designed for low resolution and do not generalize to large inputs due to their rigid architectures. They adopt downscaling or input tiling to reduce the input size, causing a loss of details and global information. There is also a lack of optical flow benchmarks to judge the actual performance of existing methods on high-resolution samples. Previous works only conducted qualitative high-resolution evaluations on hand-picked samples. This paper fills this gap in optical flow estimation in two ways. We propose DPFlow, an adaptive optical flow architecture capable of generalizing up to 8K resolution inputs while trained with only low-resolution samples. We also introduce Kubric-NK, a new benchmark for evaluating optical flow methods with input resolutions ranging from 1K to 8K. Our high-resolution evaluation pushes the boundaries of existing methods and reveals new insights about their generalization capabilities. Extensive experimental results show that DPFlow achieves state-of-the-art results on the MPI-Sintel, KITTI 2015, Spring, and other high-resolution benchmarks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。