发表机构
Shenzhen University; Shenzhen Technology University（深圳大学; 深圳技术大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对隐式神经视频表示中现有优化器收敛慢或后期振荡的问题，提出方向感知优化器DA-Lion，通过方向一致性准则和学习率感知幅度调制，在不改变模型结构下提升收敛稳定性与重建质量。
AI 中文摘要
隐式神经视频表示（NVR）将视频编码为过拟合神经网络的参数，其中训练和测试数据相同，目标是针对特定实例的信号拟合。在这种确定性机制下，优化动态直接决定了在固定预算下的重建质量，然而现有方法普遍采用为随机梯度训练设计的通用优化器。Adam系列优化器下降稳定但收敛缓慢，而Lion在早期阶段进展较快，但在后期梯度方向变得不稳定时会出现明显振荡。我们将这种不稳定性追溯到基于符号的更新对梯度-动量对齐的不敏感性。为解决此问题，我们提出了方向感知Lion（DA-Lion），一种专为NVR设计的任务驱动优化器。DA-Lion引入了（i）方向一致性准则，根据梯度-动量对齐在符号更新和动量更新之间切换，以及（ii）学习率感知的幅度调制，以稳定各训练阶段的有效步长。DA-Lion仅修改参数更新规则，保留了模型架构、参数数量、FLOPs和解码吞吐量。在三个数据集上使用四种NeRV系列骨干网络的实验表明，DA-Lion提高了收敛稳定性，并在所有骨干网络上提升了PSNR/MS-SSIM。源代码将在该https URL上提供。
英文摘要
Implicit neural video representation (NVR) encodes a video as the parameters of an overfitted neural network, where training and testing data are identical and the objective is instance-specific signal fitting. In this deterministic regime, optimization dynamics directly determine reconstruction quality under a fixed budget, yet existing methods universally adopt general-purpose optimizers designed for stochastic gradient training. Adam-family optimizers descend steadily but converge slowly, while Lion achieves faster early progress but oscillates markedly in later stages when gradient directions become unstable. We trace this instability to the insensitivity of the sign-based update to gradient--momentum alignment. To address this, we propose Direction-Aware Lion (DA-Lion), a task-driven optimizer tailored for NVR. DA-Lion introduces (i) a direction-consistency criterion that switches between sign update and momentum update based on gradient--momentum alignment, and (ii) a learning-rate-aware magnitude modulation that stabilizes effective step sizes across training phases. DA-Lion modifies only the parameter update rule, preserving model architecture, parameter count, FLOPs, and decoding throughput. Experiments on three datasets with four NeRV-family backbones show that DA-Lion improves convergence stability and boosts PSNR/MS-SSIM across all backbones. The source code will be made available at https://github.com/maoqingyu1996/DA-Lion.
CommentsPRCV2026
