Abstract
When applied sequentially to video, frame-based networks often exhibit temporal inconsistency - for example, outputs that flicker between frames. This problem is amplified when the network inputs contain time-varying corruptions. In this work, we introduce a general approach for adapting frame-based models for stable and robust inference on video. We describe a class of stability adapters that can be inserted into virtually any architecture and a resource-efficient training process that can be performed with a frozen base network. We introduce a unified conceptual framework for describing temporal stability and corruption robustness, centered on a proposed accuracy-stability-robustness loss. By analyzing the theoretical properties of this loss, we identify the conditions where it produces well-behaved stabilizer training. Our experiments validate our approach on several vision tasks including denoising (NAFNet), image enhancement (HDRNet), monocular depth (Depth Anything v2), and semantic segmentation (DeepLabv3+). Our method improves temporal stability and robustness against a range of image corruptions (including compression artifacts, noise, and adverse weather), while preserving or improving the quality of predictions.
Abstract (translated)
当顺序应用于视频时，基于帧的网络经常表现出时间上的一致性问题——例如，在帧之间闪烁的输出。当网络输入包含随时间变化的干扰时，这个问题会被放大。在这项工作中，我们介绍了一种通用方法来适应基于帧的模型，以实现对视频进行稳定和鲁棒推断。我们描述了一类可以插入几乎任何架构中的稳定性适配器，以及一个资源高效的训练过程，该过程可以在冻结的基础网络上完成。我们引入了一个统一的概念框架来描述时间上的稳定性和抗干扰性，并围绕所提出的精度-稳定-健壮损失（accuracy-stability-robustness loss）进行构建。通过分析此损失的理论性质，我们识别了它在产生良好行为的稳定性训练条件下的情况。我们的实验验证了我们在包括去噪（NAFNet）、图像增强（HDRNet）、单目深度估计（Depth Anything v2）和语义分割（DeepLabv3+）等几个视觉任务上的方法的有效性。我们的方法改善了一系列图像干扰下的时间稳定性和鲁棒性（包括压缩伪影、噪声以及恶劣天气），同时保持或提高预测的质量。
URL
https://arxiv.org/abs/2512.03014
