RetCompletion:High-Speed Inference Image Completion with Retentive Network

TL;DR

RetCompletion leverages RetNet-inspired architecture for fast, high-quality pluralistic image completion, significantly reducing inference time while maintaining strong reconstruction performance.

Contribution

This paper introduces RetCompletion, a novel two-stage framework applying RetNet to image completion, achieving high speed and quality improvements over existing methods.

Findings

Inference speed is 10x faster than ICT.

Inference speed is 15x faster than RePaint.

RetCompletion achieves high-quality image reconstruction.

Abstract

Time cost is a major challenge in achieving high-quality pluralistic image completion. Recently, the Retentive Network (RetNet) in natural language processing offers a novel approach to this problem with its low-cost inference capabilities. Inspired by this, we apply RetNet to the pluralistic image completion task in computer vision. We present RetCompletion, a two-stage framework. In the first stage, we introduce Bi-RetNet, a bidirectional sequence information fusion model that integrates contextual information from images. During inference, we employ a unidirectional pixel-wise update strategy to restore consistent image structures, achieving both high reconstruction quality and fast inference speed. In the second stage, we use a CNN for low-resolution upsampling to enhance texture details. Experiments on ImageNet and CelebA-HQ demonstrate that our inference speed is 10$\times$ faster than ICT and 15$\times$ faster than RePaint. The proposed RetCompletion significantly improves inference speed and delivers strong performance.