# Consistent Video-to-Video Translation via Explicit Correspondences

**Authors:** Gaurav Parmar, Zhengqi Li, Richard Zhang, Jun-Yan Zhu, Srinivasa Narasimhan, Eli Shechtman, Yotam Nitzan  
**Published:** 12 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.17298) · [PDF](https://arxiv.org/pdf/2611.17298) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.17298.html)

## Abstract

Interactive video-to-video applications require real-time generation while maintaining long-range temporal consistency. However, recent methods achieve speed by restricting attention to a fixed-length causal window. This limits long-range consistency whenever relevant history falls outside the context window. To address this limitation, we introduce vid2vid-long, a correspondence-based approach grounded in a simple observation. Video-to-video translation provides an explicit cross-frame reference: the regions that match in the input video should match in the output video too. Concretely, we compute patch-level correspondences in the input, guiding retrieval of previously generated outputs in the corresponding regions, and condition the model on these patches through correspondence cross-attention. Our experiments demonstrate that vid2vid-long consistently improves long-range temporal consistency across recent video models while preserving generation quality and real-time performance.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.