DA-Flow：基于扩散模型的退化感知光流估计

摘要

在高质量数据上训练的光流模型，面对真实世界中的模糊、噪声和压缩伪影等退化现象时，性能往往会严重下降。为突破这一局限，我们提出了退化感知光流这一新任务，旨在从真实世界退化视频中实现精准的密集对应关系估计。我们的核心发现是：图像复原扩散模型的中间表征本身具有退化感知能力，但缺乏时序感知能力。为此，我们通过全时空注意力机制将模型扩展至跨帧感知，并实证验证所得特征具备零样本对应关系识别能力。基于这一发现，我们提出DA-Flow混合架构，在迭代优化框架中将扩散特征与卷积特征相融合。在多个基准测试中，DA-Flow在严重退化条件下的表现显著优于现有光流方法。

English

Optical flow models trained on high-quality data often degrade severely when confronted with real-world corruptions such as blur, noise, and compression artifacts. To overcome this limitation, we formulate Degradation-Aware Optical Flow, a new task targeting accurate dense correspondence estimation from real-world corrupted videos. Our key insight is that the intermediate representations of image restoration diffusion models are inherently corruption-aware but lack temporal awareness. To address this limitation, we lift the model to attend across adjacent frames via full spatio-temporal attention, and empirically demonstrate that the resulting features exhibit zero-shot correspondence capabilities. Based on this finding, we present DA-Flow, a hybrid architecture that fuses these diffusion features with convolutional features within an iterative refinement framework. DA-Flow substantially outperforms existing optical flow methods under severe degradation across multiple benchmarks.

DA-Flow：基于扩散模型的退化感知光流估计

DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models

摘要

Support