Automatic Real-time Background Cut for Portrait Videos
arXiv:1704.08812
Abstract
We in this paper solve the problem of high-quality automatic real-time background cut for 720p portrait videos. We first handle the background ambiguity issue in semantic segmentation by proposing a global background attenuation model. A spatial-temporal refinement network is developed to further refine the segmentation errors in each frame and ensure temporal coherence in the segmentation map. We form an end-to-end network for training and testing. Each module is designed considering efficiency and accuracy. We build a portrait dataset, which includes 8,000 images with high-quality labeled map for training and testing. To further improve the performance, we build a portrait video dataset with 50 sequences to fine-tune video segmentation. Our framework benefits many video processing applications.
References in corpus (7)
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- Pyramid Scene Parsing Network
- Learning Video Object Segmentation from Static Images
- STFCN: Spatio-Temporal FCN for Semantic Video Segmentation
- Feedforward semantic segmentation with zoom-out features
- Unsupervised Video Segmentation via Spatio-Temporally Nonlocal Appearance Learning