# PEPSI++: Fast and Lightweight Network for Image Inpainting

## TL;DR

PEPSI++ introduces a fast, lightweight GAN-based image inpainting network with a novel parallel architecture and adaptive dilated convolutions, achieving high-quality results with reduced computational costs.

## Contribution

The paper proposes PEPSI++, a novel parallel inpainting network architecture and Diet-PEPSI with rate-adaptive dilated convolutions, significantly reducing hardware costs while improving inpainting quality.

## Key findings

- PEPSI++ outperforms state-of-the-art methods in PSNR and SSIM.
- PEPSI++ reduces computational time and network parameters.
- Diet-PEPSI maintains performance with fewer parameters.

## Abstract

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.