Distribution matching is central to many vision and graphics tasks, where the widely used Wasserstein distance is too costly to compute for high dimensional distributions. The Sliced Wasserstein Distance (SWD) offers a scalable alternative, yet its Monte Carlo estimator suffers from high variance, resulting in noisy gradients and slow convergence. We introduce Reservoir SWD (ReSWD), which integrates Weighted Reservoir Sampling into SWD to adaptively retain informative projection directions in optimization steps, resulting in stable gradients while remaining unbiased. Experiments on synthetic benchmarks and real-world tasks such as color correction and diffusion guidance show that ReSWD consistently outperforms standard SWD and other variance reduction baselines. Project page: https://reservoirswd.github.io/

翻译：分布匹配是许多视觉与图形学任务的核心环节，其中广泛使用的Wasserstein距离对于高维分布的计算成本过高。切片Wasserstein距离（SWD）提供了一种可扩展的替代方案，但其蒙特卡洛估计器存在高方差问题，导致梯度噪声大且收敛速度慢。本文提出储层切片Wasserstein距离（ReSWD），通过将加权储层采样整合到SWD中，在优化步骤中自适应保留信息丰富的投影方向，从而在保持无偏性的同时获得稳定的梯度。在合成基准测试以及色彩校正、扩散引导等实际任务中的实验表明，ReSWD在方差缩减方面持续优于标准SWD及其他基线方法。项目页面：https://reservoirswd.github.io/