Image-based depth-of-field rendering with non-local means filtering

We present a new approach to simulate depth-of-field effect with non-local means filtering in an unsupervised fashion which requires no user input at all. Unlike traditional rendering methods which handle the depth-of-field effect in 3D scenes, our novel approach handles the depth-of-field effect in 2D scenes. Our proposed approach mainly consists of two steps: first we extract the depth of field (DoF) region from the background in the form of alpha matte, which based on saliency detection technique and spectral matting. Then we blur the background with non-local means depth filtering, which is heavily used in image de-noising. We demonstrate our approach can precisely and efficiently simulate depth-of-field effect of images without prior knowledge of their content.