AI Paper Atlas

Research map / Video / Video generation

SPDMark: Selective Parameter Displacement for Robust Video Watermarking

Samar Fares, Nurbek Tastan, Karthik Nandakumar

CVPR 2026 · Video › Video generation · approach: Autoregressive long video generation · 3 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
increase generated frames from 8 to 32 (ablation)SPDMark · Robustness on SVD-XTRobust Acc: 0.880 -> 0.933Improved
increase generated frames from 8 to 32 (ablation)SPDMark · Clean extraction on SVD-XTBit Acc: 0.942 -> 0.996Improved
increase generated frames from 8 to 32 (ablation)SPDMark · Video quality on SVD-XTImaging Quality: 0.721 -> 0.700Hurt
raise diffusion steps from 10 to 50 (ablation)SPDMark · Clean extraction on SVD-XTBit Acc: 0.989 -> 0.995No clear effect
raise diffusion steps from 10 to 50 (ablation)SPDMark · Video quality on SVD-XTImaging Quality: 0.630 -> 0.713Improved
raise guidance scale from 1 to 5 (ablation)SPDMark · Clean extraction on SVD-XTBit Acc: 0.998 -> 0.991No clear effect
increase payload from 28 to 56 bits per frame under fixed training budget (ablation)SPDMark · Extraction accuracy on SVD-XTBit Acc and Robust AccHurt
train higher-payload variant 12k extra steps (G3) (ablation)SPDMark · Extraction on SVD-XTClean/Robust Acc: clean 0.969, robust 0.890Improved
use SPDMark instead of baselines for in-generation watermarkingVideo diffusion models · Robustness average on SVD-XTBit Acc: 0.912 -> 0.935Improved
use SPDMark instead of VideoSeal for clean extractionVideo diffusion models · Clean extraction on SVD-XTBit Acc: 0.999 -> 0.995No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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