AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

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

Mark Boss, Andreas Engelhardt, Simon Donné, Varun Jampani

ECCV 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Posterior sampling with diffusion guidance · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add ReSWD instead of standard SWD in the color matching pipeline (ablation)CDL color matching · Color matching (10 scenes)Color PSNR: 24.30 -> 24.64Improved
add ReSWD instead of standard SWD in the color matching pipeline (ablation)CDL color matching · Color matching (10 scenes)CDL error (RMSE): 0.11 -> 0.10Improved
add ReSWD instead of standard SWD in the color matching pipeline (ablation)CDL color matching · Color matching (10 scenes)Transform error (RMSE): 0.34 -> 0.31Improved
add ReSWD instead of standard SWD in the color matching pipeline (ablation)CDL color matching · Color matching (10 scenes)Time per match (s): 5 -> 5No clear effect
replace prior SDXL guidance with ReSWD modifications on the same SDXL basecolor diffusion guidance · Diffusion guidance (ContraStyles/Unsplash)Mean-W2 [10^2]: 1.941 -> 1.213Improved
replace prior SDXL guidance with ReSWD modifications on the same SDXL basecolor diffusion guidance · Diffusion guidance (ContraStyles/Unsplash)Time per generation (s): 124 -> 34Improved
upgrade base model from SDXL to SD3.5-medium with ReSWDReSWD diffusion guidance · Diffusion guidance (ContraStyles/Unsplash)CLIP-IQA: 0.696 -> 0.786Improved
use distilled SD3.5-turbo instead of SD3.5-mediumReSWD diffusion guidance · Diffusion guidance (ContraStyles/Unsplash)Mean-W2 [10^2]: 0.815 -> 0.675Improved
use SD3.5-large instead of SD3.5-mediumReSWD diffusion guidance · Diffusion guidance (ContraStyles/Unsplash)Mean-W2 [10^2]: 0.815 -> 0.55Improved
use SD3.5-large instead of SD3.5-mediumReSWD diffusion guidance · Diffusion guidance (ContraStyles/Unsplash)Time per generation (s): 32 -> 69Hurt
set number of new candidates M to 8 out of 64 total projections (ablation)ReSWD general distribution matching · General distribution matching (d=3)mean W1Improved
use too few or too many new candidates per step (ablation)ReSWD general distribution matching · General distribution matching (d=3)mean W1Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy