SwiftVR: Real-Time One-Step Generative Video Restoration

2026 paper on real-time one-step diffusion-distillation video restoration, part of emerging real-time generative VSR research line.

Link

Related resources

  • NVIDIA Maxine VFX SDK SamplesAI-powered real-time video effects (denoise, super-res, artifact removal) via Tensor Cores.
  • MoMoAAAI 2025 "Disentangled Motion Modeling for Video Frame Interpolation," diffusion-based motion disentanglement approach.
  • SparkVSRECCV 2026 interactive video super-resolution via sparse keyframe propagation, user super-resolves keyframes and it propagates the rest.
  • RIFE (ECCV2022)Real-time flow-based video frame interpolation model, widely used as the backend for many interpolation tools.
  • GPUOpen-Effects (AMD)AMD org hosting TressFX, FidelityFX-Denoiser, FSR, SSSR, SPD — real-time GPU effects libraries, cross-API.
  • CompressedVQA-AEVFull-reference + no-reference VQA for asymmetric-encoded video, QoMEX 2026 challenge solution using SigLIP2+Swin-B.
  • CAMP-VQAWACV 2026 caption-embedded multimodal no-reference VQA model for compressed video, with code and HF demo.
  • ffmpeg-queueFastify + Redis job queue for dispatching FFmpeg transcoding jobs, Docker Compose ready, production-used.
  • PXNR No-Reference Video Quality EstimationEricsson's sample implementation of the ITU-T P.NATS phase 2 no-reference video quality estimation module.
  • fssimu2Zig implementation of SSIMULACRA2 metric, ~23% faster and ~40% less memory than the reference implementation.