Need help with dain-ncnn-vulkan?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

178 Stars 13 Forks MIT License 31 Commits 18 Opened issues


DAIN, Depth-Aware Video Frame Interpolation implemented with ncnn library

Services available


Need anything else?

Contributors list

# 274
31 commits

DAIN ncnn Vulkan


ncnn implementation of DAIN, Depth-Aware Video Frame Interpolation.

dain-ncnn-vulkan uses ncnn project as the universal neural network inference framework.


Download Windows/Linux/MacOS Executable for Intel/AMD/Nvidia GPU

This package includes all the binaries and models required. It is portable, so no CUDA or Caffe runtime environment is needed :)

About DAIN

DAIN (Depth-Aware Video Frame Interpolation) (CVPR 2019)

Wenbo Bao, Wei-Sheng Lai, Chao Ma, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang

This work is developed based on our TPAMI work MEMC-Net, where we propose the adaptive warping layer. Please also consider referring to it.


Input two frame images, output one interpolated frame image.

Example Command

./dain-ncnn-vulkan -0 0.jpg -1 1.jpg -o 01.jpg
./dain-ncnn-vulkan -i input_frames/ -o output_frames/

Video Interpolation with FFmpeg

mkdir input_frames
mkdir output_frames

find the source fps and format with ffprobe, for example 24fps, AAC

ffprobe input.mp4

extract audio

ffmpeg -i input.mp4 -vn -acodec copy audio.m4a

decode all frames

ffmpeg -i input.mp4 input_frames/frame_%06d.png

interpolate 2x frame count

./dain-ncnn-vulkan -i input_frames -o output_frames

encode interpolated frames in 48fps with audio

ffmpeg -framerate 48 -i output_frames/%06d.png -i audio.m4a -c:a copy -crf 20 -c:v libx264 -pix_fmt yuv420p output.mp4

Full Usages

Usage: dain-ncnn-vulkan -0 infile -1 infile1 -o outfile [options]...
       dain-ncnn-vulkan -i indir -o outdir [options]...

-h show this help -v verbose output -0 input0-path input image0 path (jpg/png/webp) -1 input1-path input image1 path (jpg/png/webp) -i input-path input image directory (jpg/png/webp) -o output-path output image path (jpg/png/webp) or directory -n num-frame target frame count (default=N*2) -s time-step time step (0~1, default=0.5) -t tile-size tile size (>=128, default=256) can be 256,256,128 for multi-gpu -m model-path dain model path (default=best) -g gpu-id gpu device to use (default=auto) can be 0,1,2 for multi-gpu -j load:proc:save thread count for load/proc/save (default=1:2:2) can be 1:2,2,2:2 for multi-gpu -f pattern-format output image filename pattern format (%08d.jpg/png/webp, default=ext/%08d.png)

  • input0-path
    accept file path
  • input-path
    accept file directory
  • num-frame
    = target frame count
  • time-step
    = interpolation time
  • tile-size
    = tile size, use smaller value to reduce GPU memory usage, must be multiple of 32, default 256
  • load:proc:save
    = thread count for the three stages (image decoding + dain interpolation + image encoding), using larger values may increase GPU usage and consume more GPU memory. You can tune this configuration with "4:4:4" for many small-size images, and "2:2:2" for large-size images. The default setting usually works fine for most situations. If you find that your GPU is hungry, try increasing thread count to achieve faster processing.
  • pattern-format
    = the filename pattern and format of the image to be output, png is better supported, however webp generally yields smaller file sizes, both are losslessly encoded

If you encounter a crash or error, try upgrading your GPU driver:

  • Intel:
  • AMD:

Build from Source

  1. Download and setup the Vulkan SDK from

    • For Linux distributions, you can either get the essential build requirements from package manager
      dnf install vulkan-headers vulkan-loader-devel
      apt-get install libvulkan-dev
      pacman -S vulkan-headers vulkan-icd-loader
  2. Clone this project with all submodules

git clone
cd dain-ncnn-vulkan
git submodule update --init --recursive
  1. Build with CMake
    • You can pass -DUSESTATICMOLTENVK=ON option to avoid linking the vulkan loader library on MacOS
mkdir build
cd build
cmake ../src
cmake --build . -j 4


  • test-time sptial augmentation aka TTA-s
  • test-time temporal augmentation aka TTA-t

Sample Images

Original Image

origin0 origin1

Interpolate with dain

dain-ncnn-vulkan.exe -0 0.png -1 1.png -o out.png


Original DAIN Project


Other Open-Source Code Used

  • for fast neural network inference on ALL PLATFORMS
  • for encoding and decoding Webp images on ALL PLATFORMS
  • for decoding and encoding image on Linux / MacOS
  • for listing files in directory on Windows

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.