Research map / Image generation / Editing and style transfer
InOut: Diverse Image Outpainting via GAN Inversion
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use GAN inversion with coordinate-conditioned patch generation instead of an image-to-image outpainting baseline | In&Out vs Image2StyleGAN++ · Places365 | FID: 25.36 -> 23.57 | Helped |
| Use GAN inversion with coordinate-conditioned patch generation instead of an image-to-image outpainting baseline | In&Out vs Image2StyleGAN++ · Flickr-Scenery | FID: 40.39 -> 30.34 | Helped |
| Add categorical conditioning | In&Out · Places365 | IS: 7.18 -> 7.69 | Helped |
| Add categorical conditioning | In&Out · Places365 | FID: 23.57 -> 29.24 | Hurt |
| Add categorical conditioning | In&Out · Flickr-Scenery | FID: 30.34 -> 33.17 | Hurt |
| Add categorical conditioning | In&Out · Flickr-Scenery | IS: 7.16 -> 7.15 | No clear effect |
| Add latent-distance and mode-seeking diversity losses (ablation) | In&Out · Outpainting, m=2 | LPIPS: 0.183 -> 0.211 | Helped |
| Add latent-distance and mode-seeking diversity losses (ablation) | In&Out · Outpainting, m=3 | LPIPS: 0.176 -> 0.223 | Helped |
| Add mode-seeking loss (ablation) | In&Out · Outpainting, m=2 | LPIPS: 0.201 -> 0.211 | Helped |
| Add mode-seeking loss (ablation) | In&Out · Outpainting, m=3 | LPIPS: 0.206 -> 0.223 | Helped |
| Add latent-distance diversity loss (ablation) | In&Out · Outpainting, m=2 | LPIPS: 0.204 -> 0.211 | Helped |
| Add latent-distance diversity loss (ablation) | In&Out · Outpainting, m=3 | FID: 33.97 -> 30.18 | Helped |
Closest papers by meaning
- Contextual Outpainting With Object-Level Contrastive Learning (CVPR 2022 · similarity 0.90)
- Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach (ICLR 2024 · similarity 0.89)
- Image Inpainting via Iteratively Decoupled Probabilistic Modeling (ICLR 2024 · similarity 0.89)
- WarpGAN: Warping-Guided 3D GAN Inversion with Style-Based Novel View Inpainting (NeurIPS 2025 · similarity 0.87)
- Understanding the Generalization of Pretrained Diffusion Models on Out-of-Distribution Data (AAAI 2024 · similarity 0.87)
- In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing (CVPR 2024 · similarity 0.86)
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.