AI Paper Atlas

Research map / Video / Video generation

InverseCrafter: Efficient Video ReCapture as a Latent Domain Inverse Problem

Yeobin Hong, Suhyeon Lee, Hyungjin Chung, Jong Chul Ye

ECCV 2026 · Video › Video generation · approach: Efficient video diffusion models · 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
latent continuous mask + DDS guidance vs fine-tuned/optimization baselinesInverseCrafter · UltraVideo camera controlPSNR: 28.37 -> 29.35Improved
latent mask guidance instead of fine-tuned modelInverseCrafter · UltraVideo camera controlruntime: 696 s (NVS-Solver) -> 71 sImproved
add measurement guidance to base VDM (ablation)InverseCrafter · UltraVideoruntime: 70 -> 71 sNo clear effect
training-free proxy mask instead of learned mask encoder (ablation)InverseCrafter · DAVIS novel trajectoriesPSNR: 25.60 -> 25.48No clear effect
swap DDS for FlowDPS solver (ablation)InverseCrafter · DAVIS novel trajectoriesPSNR: 25.60 -> 27.43Improved
swap backbone to CogVideoX (ablation)InverseCrafter · DAVIS novel trajectoriesPSNR: 25.60 -> 26.46Improved
apply to text-guided inpainting vs VideoPainterInverseCrafter · DAVIS text-guided inpaintingFVD: 1432.77 -> 1422.72Improved
apply to text-guided inpainting vs Zero4DInverseCrafter · DAVIS text-guided inpaintingCLIP score: 25.83 vs 24.98Hurt
continuous C-channel latent mask instead of binary resized mask (ablation)InverseCrafter · DAVIS subsetmeasurement consistencyImproved
larger alpha (earlier measurement consistency step) (ablation)InverseCrafter · UltraVideoconsistency vs fidelityMixed

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