ReSWD：ReSTIR再进化，未动摇。融合储层采样与切片Wasserstein距离以实现方差降低

ReSWD: ReSTIR'd, not shaken. Combining Reservoir Sampling and Sliced Wasserstein Distance for Variance Reduction

October 1, 2025

作者: Mark Boss, Andreas Engelhardt, Simon Donné, Varun Jampani

cs.AI

摘要

分布匹配是众多视觉与图形处理任务的核心，其中广泛应用的Wasserstein距离在高维分布计算中成本过高。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。我们提出了Reservoir SWD（ReSWD），它将加权蓄水池采样融入SWD中，在优化步骤中自适应地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。在合成基准测试及色彩校正、扩散引导等实际任务中的实验表明，ReSWD始终优于标准SWD及其他方差缩减基线方法。项目页面：https://reservoirswd.github.io/

English

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/