Research map / Image generation / GANs
High-Fidelity Image Inpainting with Multimodal Guided GAN Inversion
Libo Zhang, Yongsheng Yu, Jiali Yao, Heng Fan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add gated mask-aware attention (GMA) (ablation) | MMInvertFill · Places2 (70-90% mask) | FID: 13.1843 -> 10.9116 | Improved |
| add pre-modulation (PM) (ablation) | MMInvertFill · Places2 (70-90% mask) | FID: 15.0592 -> 10.9116 | Improved |
| add soft-update mean latent (SML) (ablation) | MMInvertFill · Places2 (70-90% mask) | FID: 21.3145 -> 10.9116 | Improved |
| add F&W+ latent space (ablation) | MMInvertFill · Places2 (70-90% mask) | FID: 31.4058 -> 10.9116 | Improved |
| add F&W+ latent space (ablation) | MMInvertFill · Places2 (70-90% mask) | LPIPS: 0.4258 -> 0.3531 | Improved |
| add edge and segmentation unbiased guidance (ablation) | MMInvertFill · OST | FID: 14.9313 -> 10.1012 | Improved |
| add segmentation guidance only (ablation) | MMInvertFill · OST | FID: 14.9313 -> 12.8401 | Improved |
| add edge guidance only (ablation) | MMInvertFill · OST | FID: 14.9313 -> 13.7514 | Improved |
| use unbiased instead of biased predicted guidance (ablation) | MMInvertFill · OST | FID: 12.0157 -> 10.1012 | Improved |
| use ground-truth auxiliary guidance (ablation) | MMInvertFill · OST | FID: 10.1012 -> 8.1642 | Improved |
| use GMA+ADN fusion instead of GMA+add (ablation) | MMInvertFill · OST | FID: 17.84 -> 15.74 | Improved |
| use ADN instead of AdaIN in GMA (ablation) | MMInvertFill · OST | FID: 18.59 -> 15.74 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- ZITS — ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priors (TPAMI 2023) · better on 2 of 2 shared results
- MISF — MISF: Multi-Level Interactive Siamese Filtering for High-Fidelity Image Inpainting (CVPR 2022) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- High-Fidelity Image Inpainting with GAN Inversion (ECCV 2022 · similarity 0.97)
- Diverse Inpainting and Editing with GAN Inversion (ICCV 2023 · similarity 0.93)
- In-Domain GAN Inversion for Faithful Reconstruction and Editability (TPAMI 2024 · similarity 0.92)
- In-Domain GAN Inversion for Real Image Editing (ECCV 2020 · similarity 0.92)
- WarpGAN: Warping-Guided 3D GAN Inversion with Style-Based Novel View Inpainting (NeurIPS 2025 · similarity 0.91)
- In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing (CVPR 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
