RobustVideoMatting
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
Install / Use
/learn @PeterL1n/RobustVideoMattingREADME
Robust Video Matting (RVM)
Official repository for the paper Robust High-Resolution Video Matting with Temporal Guidance. RVM is specifically designed for robust human video matting. Unlike existing neural models that process frames as independent images, RVM uses a recurrent neural network to process videos with temporal memory. RVM can perform matting in real-time on any videos without additional inputs. It achieves 4K 76FPS and HD 104FPS on an Nvidia GTX 1080 Ti GPU. The project was developed at ByteDance Inc.
<br>News
- [Nov 03 2021] Fixed a bug in train.py.
- [Sep 16 2021] Code is re-released under GPL-3.0 license.
- [Aug 25 2021] Source code and pretrained models are published.
- [Jul 27 2021] Paper is accepted by WACV 2022.
Showreel
Watch the showreel video (YouTube, Bilibili) to see the model's performance.
<p align="center"> <a href="https://youtu.be/Jvzltozpbpk"> <img src="documentation/image/showreel.gif"> </a> </p>All footage in the video are available in Google Drive.
<br>Demo
- Webcam Demo: Run the model live in your browser. Visualize recurrent states.
- Colab Demo: Test our model on your own videos with free GPU.
Download
We recommend MobileNetv3 models for most use cases. ResNet50 models are the larger variant with small performance improvements. Our model is available on various inference frameworks. See inference documentation for more instructions.
<table> <thead> <tr> <td>Framework</td> <td>Download</td> <td>Notes</td> </tr> </thead> <tbody> <tr> <td>PyTorch</td> <td> <a href="https://github.com/PeterL1n/RobustVideoMatting/releases/download/v1.0.0/rvm_mobilenetv3.pth">rvm_mobilenetv3.pth</a><br> <a href="https://github.com/PeterL1n/RobustVideoMatting/releases/download/v1.0.0/rvm_resnet50.pth">rvm_resnet50.pth</a> </td> <td> Official weights for PyTorch. <a href="documentation/inference.md#pytorch">Doc</a> </td> </tr> <tr> <td>TorchHub</td> <td> Nothing to Download. </td> <td> Easiest way to use our model in your PyTorch project. <a href="documentation/inference.md#torchhub">Doc</a> </td> </tr> <tr> <td>TorchScript</td> <td> <a href="https://github.com/PeterL1n/RobustVideoMatting/releases/download/v1.0.0/rvm_mobilenetv3_fp32.torchscript">rvm_mobilenetv3_fp32.torchscript</a><br> <a href="https://github.com/PeterL1n/RobustVideoMatting/releases/download/v1.0.0/rvm_mobilenetv3_fp16.torchscript">rvm_mobilenetv3_fp16.torchscript</a><br> <a href="https://github.com/PeterL1n/RobustVideoMatting/releases/download/v1.0.0/rvm_resnet50_fp32.torchscript">rvm_resnet50_fp32.torchscript</a><br> <a href="https://github.com/PeterL1n/RobustVideoMatting/releases/download/v1.0.0/rvm_resnet50_fp16.torchscript">rvm_resnet50_fp16.torchscript</a> </td> <td> If inference on mobile, consider export int8 quantized models yourself. <a href="documentation/inference.md#torchscript">Doc</a> </td> </tr> <tr> <td>ONNX</td> <td> <a href="https://github.com/PeterL1n/RobustVideoMatting/releases/download/v1.0.0/rvm_mobilenetv3_fp32.onnx">rvm_mobilenetv3_fp32.onnx</a><br> <a href="https://github.com/PeterL1n/RobustVideoMatting/releases/download/v1.0.0/rvm_mobilenetv3_fp16.onnx">rvm_mobilenetv3_fp16.onnx</a><br> <a href="https://github.com/PeterL1n/RobustVideoMatting/releases/download/v1.0.0/rvm_resnet50_fp32.onnx">rvm_resnet50_fp32.onnx</a><br> <a href="https://github.com/PeterL1n/RobustVideoMatting/releases/download/v1.0.0/rvm_resnet50_fp16.onnx">rvm_resnet50_fp16.onnx</a> </td> <td> Tested on ONNX Runtime with CPU and CUDA backends. Provided models use opset 12. <a href="documentation/inference.md#onnx">Doc</a>, <a href="https://github.com/PeterL1n/RobustVideoMatting/tree/onnx">Exporter</a>. </td> </tr> <tr> <td>TensorFlow</td> <td> <a href="https://github.com/PeterL1n/RobustVideoMatting/releases/download/v1.0.0/rvm_mobilenetv3_tf.zip">rvm_mobilenetv3_tf.zip</a><br> <a href="https://github.com/PeterL1n/RobustVideoMatting/releases/download/v1.0.0/rvm_resnet50_tf.zip">rvm_resnet50_tf.zip</a> </td> <td> TensorFlow 2 SavedModel. <a href="documentation/inference.md#tensorflow">Doc</a> </td> </tr> <tr> <td>TensorFlow.js</td> <td> <a href="https://github.com/PeterL1n/RobustVideoMatting/releases/download/v1.0.0/rvm_mobilenetv3_tfjs_int8.zip">rvm_mobilenetv3_tfjs_int8.zip</a><br> </td> <td> Run the model on the web. <a href="https://peterl1n.github.io/RobustVideoMatting/#/demo">Demo</a>, <a href="https://github.com/PeterL1n/RobustVideoMatting/tree/tfjs">Starter Code</a> </td> </tr> <tr> <td>CoreML</td> <td> <a href="https://github.com/PeterL1n/RobustVideoMatting/releases/download/v1.0.0/rvm_mobilenetv3_1280x720_s0.375_fp16.mlmodel">rvm_mobilenetv3_1280x720_s0.375_fp16.mlmodel</a><br> <a href="https://github.com/PeterL1n/RobustVideoMatting/releases/download/v1.0.0/rvm_mobilenetv3_1280x720_s0.375_int8.mlmodel">rvm_mobilenetv3_1280x720_s0.375_int8.mlmodel</a><br> <a href="https://github.com/PeterL1n/RobustVideoMatting/releases/download/v1.0.0/rvm_mobilenetv3_1920x1080_s0.25_fp16.mlmodel">rvm_mobilenetv3_1920x1080_s0.25_fp16.mlmodel</a><br> <a href="https://github.com/PeterL1n/RobustVideoMatting/releases/download/v1.0.0/rvm_mobilenetv3_1920x1080_s0.25_int8.mlmodel">rvm_mobilenetv3_1920x1080_s0.25_int8.mlmodel</a><br> </td> <td> CoreML does not support dynamic resolution. Other resolutions can be exported yourself. Models require iOS 13+. <code>s</code> denotes <code>downsample_ratio</code>. <a href="documentation/inference.md#coreml">Doc</a>, <a href="https://github.com/PeterL1n/RobustVideoMatting/tree/coreml">Exporter</a> </td> </tr> </tbody> </table>All models are available in Google Drive and Baidu Pan (code: gym7).
<br>PyTorch Example
- Install dependencies:
pip install -r requirements_inference.txt
- Load the model:
import torch
from model import MattingNetwork
model = MattingNetwork('mobilenetv3').eval().cuda() # or "resnet50"
model.load_state_dict(torch.load('rvm_mobilenetv3.pth'))
- To convert videos, we provide a simple conversion API:
from inference import convert_video
convert_video(
model, # The model, can be on any device (cpu or cuda).
input_source='input.mp4', # A video file or an image sequence directory.
output_type='video', # Choose "video" or "png_sequence"
output_composition='com.mp4', # File path if video; directory path if png sequence.
output_alpha="pha.mp4", # [Optional] Output the raw alpha prediction.
output_foreground="fgr.mp4", # [Optional] Output the raw foreground prediction.
output_video_mbps=4, # Output video mbps. Not needed for png sequence.
downsample_ratio=None, # A hyperparameter to adjust or use None for auto.
seq_chunk=12, # Process n frames at once for better parallelism.
)
- Or write your own inference code:
from torch.utils.data import DataLoader
from torchvision.transforms import ToTensor
from inference_utils import VideoReader, VideoWriter
reader = VideoReader('input.mp4', transform=ToTensor())
writer = VideoWriter('output.mp4', frame_rate=30)
bgr = torch.tensor([.47, 1, .6]).view(3, 1, 1).cuda() # Green background.
rec = [None] * 4 # Initial recurrent states.
downsample_ratio = 0.25 # Adjust based on your video.
with torch.no_grad():
for src in DataLoader(reader): # RGB tensor normalized to 0 ~ 1.
fgr, pha, *rec = model(src.cuda(), *rec, downsample_ratio) # Cycle the recurrent states.
com = fgr * pha + bgr * (1 - pha) # Composite to green background.
writer.write(com) # Write frame.
- The models and converter API are also available through TorchHub.
# Load the model.
model = torch.hub.load("PeterL1n/RobustVideoMatting", "mobilenetv3") # or "resnet50"
# Converter API.
convert_video = torch.hub.load("PeterL1n/RobustVideoMatting", "converter")
Please see inference documentation for details on downsample_ratio hyperparameter, more converter arguments, and more
