AI Paper Atlas

Research map / Video / Video generation

Consistent Video-to-Video Translation via Explicit Correspondences

Gaurav Parmar, Zhengqi Li, Richard Zhang, Jun-Yan Zhu, Srinivasa G. Narasimhan, Eli Shechtman, Yotam Nitzan

ECCV 2026 · Video › Video generation · approach: Autoregressive long video generation · 0 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 correspondence retrieval memory to Rolling Forcing (ablation)Rolling Forcing · VACE-BenchmarkLPIPS: 0.427 -> 0.240Improved
add correspondence memory (ablation)Self-Forcing · VACE-BenchmarkLPIPS: 0.548 -> 0.343Improved
add correspondence memory (ablation)LongLive · VACE-BenchmarkLPIPS: 0.511 -> 0.272Improved
add correspondence memory (ablation)Self-Forcing · DL3DVLPIPS: 0.616 -> 0.451Improved
add correspondence memory (ablation)Rolling Forcing · DL3DVLPIPS: 0.445 -> 0.305Improved
add correspondence patches and cross-attention (ablation)Ours · VACE-BenchmarkLPIPS: 0.379 -> 0.240Improved
add correspondence patches and cross-attention (ablation)Ours · VACE-BenchmarkDreamSim: 0.160 -> 0.066Improved
add correspondence patches (ablation)Ours · VACE-BenchmarkQuality Score: 0.829 -> 0.828No clear effect
enlarge KV cache window 2x to 4x (ablation)Self-Forcing · DL3DVLPIPS: 0.710 -> 0.759Hurt
enlarge KV cache window 4x (ablation)Self-Forcing · VACE-BenchmarkLPIPS: 0.35 -> 0.33Mixed
global average-pooled KV cache (ablation)Self-Forcing · VACE-BenchmarkQuality: 0.753Hurt
replace similarity retrieval with random retrieval (ablation)Ours · VACE-BenchmarkLPIPS: 0.240 -> 0.396Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 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