Long-Range Feature Propagating for Natural Image Matting
This work solves the problem of inaccurate alpha matte estimation in image matting for computer vision applications, representing an incremental improvement by addressing a specific bottleneck in existing deep learning methods.
The paper tackles the problem of natural image matting, where over 50% of pixels in unknown regions cannot be correlated to known regions due to limited receptive fields in CNNs, leading to inaccurate alpha value estimation. The proposed Long-Range Feature Propagating Network (LFPNet) addresses this by learning long-range context features, achieving favorable performance against state-of-the-art methods on AlphaMatting and Adobe Image Matting datasets.
Natural image matting estimates the alpha values of unknown regions in the trimap. Recently, deep learning based methods propagate the alpha values from the known regions to unknown regions according to the similarity between them. However, we find that more than 50\% pixels in the unknown regions cannot be correlated to pixels in known regions due to the limitation of small effective reception fields of common convolutional neural networks, which leads to inaccurate estimation when the pixels in the unknown regions cannot be inferred only with pixels in the reception fields. To solve this problem, we propose Long-Range Feature Propagating Network (LFPNet), which learns the long-range context features outside the reception fields for alpha matte estimation. Specifically, we first design the propagating module which extracts the context features from the downsampled image. Then, we present Center-Surround Pyramid Pooling (CSPP) that explicitly propagates the context features from the surrounding context image patch to the inner center image patch. Finally, we use the matting module which takes the image, trimap and context features to estimate the alpha matte. Experimental results demonstrate that the proposed method performs favorably against the state-of-the-art methods on the AlphaMatting and Adobe Image Matting datasets.