CVIVMay 22, 2019

PEPSI++: Fast and Lightweight Network for Image Inpainting

arXiv:1905.09010v5108 citations
Originality Incremental advance
AI Analysis

This work addresses efficiency issues in image inpainting for applications requiring fast processing, though it is incremental as it builds on existing coarse-to-fine networks.

The authors tackled the problem of high computational costs in GAN-based image inpainting methods by proposing PEPSI and Diet-PEPSI, which improved PSNR and SSIM scores while significantly reducing hardware costs like computational time and network parameters.

Among the various generative adversarial network (GAN)-based image inpainting methods, a coarse-to-fine network with a contextual attention module (CAM) has shown remarkable performance. However, owing to two stacked generative networks, the coarse-to-fine network needs numerous computational resources such as convolution operations and network parameters, which result in low speed. To address this problem, we propose a novel network architecture called PEPSI: parallel extended-decoder path for semantic inpainting network, which aims at reducing the hardware costs and improving the inpainting performance. PEPSI consists of a single shared encoding network and parallel decoding networks called coarse and inpainting paths. The coarse path produces a preliminary inpainting result to train the encoding network for the prediction of features for the CAM. Simultaneously, the inpainting path generates higher inpainting quality using the refined features reconstructed via the CAM. In addition, we propose Diet-PEPSI that significantly reduces the network parameters while maintaining the performance. In Diet-PEPSI, to capture the global contextual information with low hardware costs, we propose novel rate-adaptive dilated convolutional layers, which employ the common weights but produce dynamic features depending on the given dilation rates. Extensive experiments comparing the performance with state-of-the-art image inpainting methods demonstrate that both PEPSI and Diet-PEPSI improve the qualitative scores, i.e. the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM), as well as significantly reduce hardware costs such as computational time and the number of network parameters.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes