Research map / Image generation / Image restoration
Progressive Artwork Outpainting via Latent Diffusion Models
Dae-Young Song, Jung-Jae Yu, Donghyeon Cho
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 fusion-based composition planning module to SD inpainting (ablation) | SD Inpainting · IconArt (6,528 images, inner-area outpainting) | FID: 30.82 -> 21.91 | Improved |
| add ControlNet-based composition planning module to SD inpainting (ablation) | SD Inpainting · IconArt (6,528 images, inner-area outpainting) | FID: 30.82 -> 24.38 | Improved |
| add fusion-based composition planning module to SD inpainting (ablation) | SD Inpainting · IconArt (6,528 images, inner-area outpainting) | CLIP-S: 0.278 -> 0.293 | Improved |
| add ControlNet-based composition planning module to SD inpainting (ablation) | SD Inpainting · IconArt (6,528 images, inner-area outpainting) | CLIP-AES: 6.653 -> 6.997 | Improved |
| use fusion-based instead of ControlNet-based planning (ablation) | Ours · IconArt (6,528 images, inner-area outpainting) | FID: 24.38 -> 21.91 | Improved |
| use fusion-based instead of ControlNet-based planning (ablation) | Ours · IconArt (6,528 images, inner-area outpainting) | CLIP-AES: 6.997 -> 6.964 | Hurt |
| add fusion-based composition planning to SD inpainting (ablation) | SD Inpainting · Wikiart (400 unseen images, outer-area outpainting, r=1) | Blurriness: 821.29 -> 873.56 | Improved |
| add ControlNet-based composition planning to SD inpainting (ablation) | SD Inpainting · Wikiart (400 unseen images, outer-area outpainting, r=1) | CLIP-AES: 6.644 -> 7.015 | Improved |
| progressive SD-based outpainting with fusion planning instead of Firefly | Firefly · Wikiart (400 unseen images, outer-area outpainting, r=1) | Blurriness: 617.51 -> 873.56 | Improved |
| increase generation ratio from 200% to 600% (ablation) | SD Inpainting · Wikiart (400 unseen images, outer-area outpainting) | Blurriness: 888.89 -> 690.88 | Hurt |
| increase generation ratio from 200% to 600% (ablation) | Ours (ControlNet) · Wikiart (400 unseen images, outer-area outpainting) | Blurriness: 886.92 -> 719.47 | Hurt |
| increase generation ratio from 200% to 600% (ablation) | Ours (Fusion) · Wikiart (400 unseen images, outer-area outpainting) | Blurriness: 907.63 -> 747.35 | Hurt |
Closest papers by meaning
- Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach (ICLR 2024 · similarity 0.88)
- TD-Paint: Faster Diffusion Inpainting Through Time-Aware Pixel Conditioning (ICLR 2025 · similarity 0.88)
- Infinite-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation (AAAI 2025 · similarity 0.88)
- RAD: Region-Aware Diffusion Models for Image Inpainting (CVPR 2025 · similarity 0.87)
- Image Inpainting via Tractable Steering of Diffusion Models (ICLR 2024 · similarity 0.87)
- PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference (NeurIPS 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.
