Progressive Artwork Outpainting Via Latent Diffusion Models
Dae-Young Song, Jung-Jae Yu, Donghyeon Cho
Abstract
Figure 1. Outpainting comparisons between single-step (a) and progressive approaches (b,c). (a) Results of the single-step outpainting. We first resize the input image to a fixed size suitable for a conventional outpainting model, and then apply outpainting. After that, we revert the image to its original aspect ratio. Finally, we use a super-resolution model to restore the reduced resolution. (b) Results of progressive outpainting without consideration of overall composition. (c) Results of our method with global context consideration and planning. The red bounding boxes indicate the inputs.
Progressive approach enables outpainting in any direction and produces high-fidelity, high-resolution images with no restrictions on aspect ratio. Furthermore, our method produces globally harmonious outpainting results compared to models that do not take overall composition into account.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers1
Ask how each one uses itBuilds on30
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- Diffusion Models Beat GANs on Image SynthesisPrafulla Dhariwal, Alexander Quinn NicholNeurIPS 2021 · 13,211 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 11,743 citations
Related papers
- Unboxed: Geometrically and Temporally Consistent Video OutpaintingZhongrui Yu, Martina Megaro-Boldini, Robert W. Sumner, Abdelaziz DjelouahCVPR 2025
- Very Long Natural Scenery Image Prediction by OutpaintingZongxin Yang, Jian Dong, Ping Liu, Yi Yang et al.ICCV 2019 · 97 citations
- InOut: Diverse Image Outpainting via GAN InversionYen-Chi Cheng, Chieh Hubert Lin, Hsin-Ying Lee, Jian Ren et al.CVPR 2022 · 72 citations
- Painting from PartDongsheng Guo, Haoru Zhao, Yunhao Cheng, Haiyong Zheng et al.ICCV 2021 · 2 citations
- Infinite-Canvas: Higher-Resolution Video Outpainting with Extensive Content GenerationQihua Chen, Yue Ma, Hongfa Wang, Junkun Yuan et al.AAAI 2025 · 4 citations
