English

Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing

Computer Vision and Pattern Recognition 2024-02-23 v1 Artificial Intelligence

Abstract

GAN-based image attribute editing firstly leverages GAN Inversion to project real images into the latent space of GAN and then manipulates corresponding latent codes. Recent inversion methods mainly utilize additional high-bit features to improve image details preservation, as low-bit codes cannot faithfully reconstruct source images, leading to the loss of details. However, during editing, existing works fail to accurately complement the lost details and suffer from poor editability. The main reason is they inject all the lost details indiscriminately at one time, which inherently induces the position and quantity of details to overfit source images, resulting in inconsistent content and artifacts in edited images. This work argues that details should be gradually injected into both the reconstruction and editing process in a multi-stage coarse-to-fine manner for better detail preservation and high editability. Therefore, a novel dual-stream framework is proposed to accurately complement details at each stage. The Reconstruction Stream is employed to embed coarse-to-fine lost details into residual features and then adaptively add them to the GAN generator. In the Editing Stream, residual features are accurately aligned by our Selective Attention mechanism and then injected into the editing process in a multi-stage manner. Extensive experiments have shown the superiority of our framework in both reconstruction accuracy and editing quality compared with existing methods.

Keywords

Cite

@article{arxiv.2402.14398,
  title  = {Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing},
  author = {Hao Li and Mengqi Huang and Lei Zhang and Bo Hu and Yi Liu and Zhendong Mao},
  journal= {arXiv preprint arXiv:2402.14398},
  year   = {2024}
}

Comments

18 pages, 18 figures, published to AAAI24

R2 v1 2026-06-28T14:56:50.690Z