Zhang, Ziqiang;
Yan, Yan;
Xue, Jing-Hao;
Wang, Hanzi;
(2024)
Spatial-Contextual Discrepancy Information Compensation for GAN Inversion.
In:
Proceedings of the AAAI Conference on Artificial Intelligence.
(pp. pp. 7432-7440).
Association for the Advancement of Artifcial Intelligence (AAAI): Vancouver, Canada.
Preview |
Text
2312.07079.pdf - Accepted Version Download (11MB) | Preview |
Abstract
Most existing GAN inversion methods either achieve accurate reconstruction but lack editability or offer strong editability at the cost of fidelity. Hence, how to balance the distortioneditability trade-off is a significant challenge for GAN inversion. To address this challenge, we introduce a novel spatial-contextual discrepancy information compensationbased GAN-inversion method (SDIC), which consists of a discrepancy information prediction network (DIPN) and a discrepancy information compensation network (DICN). SDIC follows a “compensate-and-edit” paradigm and successfully bridges the gap in image details between the original image and the reconstructed/edited image. On the one hand, DIPN encodes the multi-level spatial-contextual information of the original and initial reconstructed images and then predicts a spatial-contextual guided discrepancy map with two hourglass modules. In this way, a reliable discrepancy map that models the contextual relationship and captures finegrained image details is learned. On the other hand, DICN incorporates the predicted discrepancy information into both the latent code and the GAN generator with different transformations, generating high-quality reconstructed/edited images. This effectively compensates for the loss of image details during GAN inversion. Both quantitative and qualitative experiments demonstrate that our proposed method achieves the excellent distortion-editability trade-off at a fast inference speed for both image inversion and editing tasks. Our code is available at https://github.com/ZzqLKED/SDIC.
| Type: | Proceedings paper |
|---|---|
| Title: | Spatial-Contextual Discrepancy Information Compensation for GAN Inversion |
| Event: | The Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24) |
| Dates: | 22 Feb 2024 - 25 Feb 2024 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1609/aaai.v38i7.28574 |
| Publisher version: | https://doi.org/10.1609/aaai.v38i7.28574 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10187928 |
Archive Staff Only
 |
View Item |
