AI Paper Atlas

Research map / Video / Video generation

FreeViS: Training-free Video Stylization with Inconsistent References

Jiacong Xu, Yiqun Mei, Ke Zhang, Vishal M. Patel

ICLR 2026 · Video › Video generation · approach: Autoregressive long video generation · 6 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
use multiple stylized references instead of a single first-frame reference (vs AnyV2V* re-implementation)FreeViS · Video style transfer (200 videos)Style Consistency: 0.675 -> 0.898Improved
use FreeViS instead of AnyV2V* on the same base modelI2V stylization · Video style transfer (200 videos)Human preference: 3.372 -> 4.113Improved
use FreeViS instead of AnyV2V*I2V stylization · Video style transfer (200 videos)Flow Consistency (EPE): 1.103 -> 0.641Improved
use FreeViS instead of AnyV2V*I2V stylization · Video style transfer (200 videos)LPIPS: 0.218 -> 0.479No clear effect
use FreeViS instead of AnyV2V*I2V stylization · Video style transfer (200 videos)FID: 27.59 -> 21.62Improved
add IHC (high-frequency compensation) for layout reconstruction (ablation)FreeViS · Video style transfer (200 videos)qualitative layout fidelityImproved
add extra reference frames (ablation)FreeViS · Video style transfer (200 videos)qualitative style consistencyImproved
add EOG (flow-based motion cues) for plain regions (ablation)FreeViS · Video style transfer (200 videos)flow consistency and stylization qualityImproved
apply FreeViS on Wan2.1 videos instead of StyleCrafterstylized T2V · Stylized T2V generation (200 prompts)Dynamic Quality: 0.368 -> 0.509Improved
apply FreeViS on Wan2.1 videos instead of StyleCrafterstylized T2V · Stylized T2V generation (200 prompts)CSD Score: 0.515 -> 0.437Hurt
apply FreeViS on top of AnyV2V* implementationFreeViS · Video style transfer (200 videos)inference time: approximately 30% overheadHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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