genai-video-super-resolution

AWS sample pipeline combining Real-ESRGAN and SwinIR to upscale low-resolution video up to 4x using AWS services.

Link

Related resources

  • RIFE (ECCV2022)Real-time flow-based video frame interpolation model, widely used as the backend for many interpolation tools.
  • AI-Youtube-Shorts-GeneratorLLM-driven highlight detection with Whisper transcription and automatic vertical cropping to turn long videos into shorts, MIT-licensed wit…
  • FILM: Frame Interpolation for Large MotionGoogle Research's unified neural network for video frame interpolation handling large motion without requiring optical flow or depth estima…
  • Track-AnythingInteractive video object tracking and segmentation tool built on Segment Anything, XMem, and E2FGVI, feeding video inpainting pipelines.
  • ProPainterICCV 2023 video inpainting tool for object removal/completion using propagation and transformer-based approach, CLI-usable.
  • PXNR No-Reference Video Quality EstimationEricsson's sample implementation of the ITU-T P.NATS phase 2 no-reference video quality estimation module.
  • nr-vqa-consumervideoNo-reference video quality metric tuned for consumer video capture artifacts (sensor noise, motion blur, shake) rather than compression art…
  • aws-batch-with-FFmpegReference architecture running FFmpeg containers (ARM64/x86-64/NVIDIA/Xilinx) on AWS Batch with Spot compute environments and SDK/REST job…
  • ffmpeg-queueFastify + Redis job queue for dispatching FFmpeg transcoding jobs, Docker Compose ready, production-used.
  • fssimu2Zig implementation of SSIMULACRA2 metric, ~23% faster and ~40% less memory than the reference implementation.