VideoGigaGAN: Towards Detail-rich Video Super-Resolution

Yiran Xu, Taesung Park, Richard Zhang, Yang Zhou, Eli Shechtman +3 more
2/9/2026

No official code found. Best implementation: BaIGaO/VideoGigaGAN (3 stars, MIT, last commit 2025-10-14).

Abstract

Video super-resolution (VSR) models achieve temporal consistency but often produce blurrier results than their image-based counterparts due to limited generative capacity. This prompts the question: can we adapt a generative image upsampler for VSR while preserving temporal consistency? We introduce VideoGigaGAN, a new generative VSR model that combines high-frequency detail with temporal stability, building on the large-scale GigaGAN image upsampler. Simple adaptations of GigaGAN for VSR led to flickering issues, so we propose techniques to enhance temporal consistency. We validate the effectiveness of VideoGigaGAN by comparing it with state-of-the-art VSR models on public datasets and showcasing video results with 8× upsampling.

View on arXivView PDF

Code Implementations(1)

BaIGaO/VideoGigaGANCommunity55%
MIT

This repository provides an unofficial implementation of the paper VideoGigaGAN: Towards Detail-rich Video Super-Resolution, aiming to achieve high-quality, detail-rich video super-resolution (VSR).

30PythonSep 28, 20251 years agoMIT

Similar Papers

One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution

86% match1 repo3562025

ControlSR: Taming Diffusion Models for Consistent Real-World Image Super Resolution

86% match1 repo132024

Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors

85% match1 repo1802026

NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-Resolution

85% match1 repo272025

BasicAVSR: Arbitrary-Scale Video Super-Resolution via Image Priors and Enhanced Motion Compensation

85% match1 repo132025

DiffVSR: Revealing an Effective Recipe for Taming Robust Video Super-Resolution Against Complex Degradations

85% match2025

Cite this paper

@article{xu2026videogigagan,
  title  = {VideoGigaGAN: Towards Detail-rich Video Super-Resolution},
  author = {Yiran Xu and Taesung Park and Richard Zhang and Yang Zhou and Eli Shechtman and Feng Liu and Jia-Bin Huang and Difan Liu},
  year   = {2026},
  eprint = {2404.12388},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2404.12388},
  journal = {CVPR 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2404.12388.svg)](https://codeofpaper.com/paper/2404.12388)

Discussion