AI Paper Atlas

Research map / Video / Video generation

Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-Turn Editing

Dohun Lee, Chun-Hao Huang, Xuelin Chen, Jong Chul Ye, Duygu Ceylan, Hyeonho Jeong

ECCV 2026 · Video › Video generation · approach: Efficient video diffusion models · 5 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 video FOV retrieval to dynamic tokenization (ablation)Memory-V2V · Component ablation (5th iteration)MEt3R (1st vs 5th): 0.2234 -> 0.2169Improved
add adaptive token merging to dynamic tokenization (ablation)Memory-V2V · Component ablation (5th iteration)time (s): 980.80 -> 661.31Improved
add adaptive token merging without retrieval (ablation)Memory-V2V · Component ablation (5th iteration)MEt3R (1st vs 5th): 0.2234 -> 0.2344Hurt
combine retrieval and token merging (full model) (ablation)Memory-V2V · Component ablation (5th iteration)time (s): 980.80 -> 648.5Improved
use Memory-V2V instead of independent ReCamMasterReCamMaster · Multi-turn NVSMEt3R avg consistency: 0.1892 -> 0.1357Improved
use memory instead of autoregressive chaining of ReCamMasterReCam (AR) · Multi-turn NVSMEt3R 1st vs 3rd iter: 0.1985 -> 0.1525Improved
add memory to ReCamMaster for camera accuracyReCamMaster · Multi-turn NVSTransErr: 24.23 -> 13.47Improved
retrieve top-3 instead of top-1 memory video (ablation)Memory-V2V · MultiCamVideo GT comparisonPSNR: 17.15 -> 18.05Improved
add memory to LucyEdit for long video editingLucyEdit · Long video editingSubject Consistency: 0.8683 -> 0.9326Improved
Memory-V2V vs FlowEdit on cross-frame DINO/CLIP similarityMemory-V2V · Long video editingDINO-F: 0.8612 -> 0.8019Hurt
merge or discard highly responsive tokens (ablation)Memory-V2V · qualitative token reductioncross-turn consistencyHurt
merge low-responsive tokens instead of discarding them (ablation)Memory-V2V · qualitative token reductionvisual fidelityImproved

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