Researchers from Adobe Research and The Chinese University of Hong Kong created an algorithm that automatically separates subjects from their backgrounds so you can easily replace the background and apply filters to the subject.
Their research paper mentions there are good user-guided tools that support manually creating masks to separate subjects from the background, but the “tools are tedious and difficult to use, and remain an obstacle for casual photographers who want their portraits to look good.”
Using a TITAN X GPU and the cuDNN-accelerated Caffe deep learning framework, the researchers trained their convolutional neural network on 1,800 portrait images from Flickr. Their GPU-accelerated method was 20x faster than a CPU-only approach.
Portrait video segmentation is next on the radar for the researchers.
Read more >>
New Deep Learning Method Enhances Your Selfies
Jul 05, 2016
Discuss (0)
AI-Generated Summary
- Researchers from Adobe Research and The Chinese University of Hong Kong developed an algorithm that automatically separates portrait subjects from backgrounds for easy replacement and filtering.
- The research paper notes that existing manual masking tools are tedious and difficult for casual photographers.
- Training used a TITAN X GPU with the cuDNN-accelerated Caffe deep learning framework on 1,800 Flickr portrait images, achieving 20x speedup over CPU-only methods.
- Portrait video segmentation is the next research target for the team.
Next Step
- Read the Digital Trends coverage for additional details on the automatic portrait clipping research.
Powered by NVIDIA Nemotron. AI-generated content may summarize information incompletely. Verify important information. Learn more
About the Authors
