{"repo":"taco-group/SparkVSR","free":true,"listed":false,"github":"https://github.com/taco-group/SparkVSR","clone":"git clone https://github.com/taco-group/SparkVSR.git","description":"[ECCV 2026] SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation","language":"Python","stars":695,"topics":["artificial-intelligence","generative-ai","generative-models","image-processing","llm","machine-learning","restoration","super-resolution","vfx","video"],"license":"Apache-2.0","category":"media-processing","readme_excerpt":"SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation Jiongze Yu 1 , Xiangbo Gao 1 , Pooja Verlani 2 , Akshay Gadde 2 , Yilin Wang 2 , Balu Adsumilli 2 , Zhengzhong Tu †,1 1 Texas A&M University    2 YouTube, Google † Corresponding author Accepted to ECCV 2026       💡 Your ⭐ star means a lot to us and helps support the continuous development of this project! 📰 News - 2026.08.03: SparkVSR is now available on Papers with Code, with 14 verified evaluations. Thanks to the Hugging Face open-source team for curating and verifying the results! - 2026.06.20: SparkVSR is now available on RunningHub.ai and CNAPS.ai via community deployments! - 2026.06.18: SparkVSR is accepted to ECCV 2026! 🎉🎉🎉 - 2026.05.11: ComfyUI-SparkVSR is released.🚀🚀🚀 - 2026.03.17: This repo is released.🔥🔥🔥 --- Demo --- Abstract: Video Super-Resolution (VSR) aims to restore high-quality video frames from low-resolution (LR) estimates, yet most existing VSR approaches behave like black boxes at inference time: users cannot reliably correct unexpected artifacts, but instead can only accept whatever the model produces. In this paper, we propose a novel interactive VSR framework dubbed SparkVSR that makes sparse keyframes a simple and expressive control signal. Specifically, users can first super-resolve or optionally a small set of keyframes using any off-the-shelf image super-resolution (ISR) model, then SparkVSR propagates the keyframe priors to the ent","default_branch":null,"files":null,"tree":[],"storefront":"/r/taco-group","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/taco-group/SparkVSR/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}