English

Texture Hallucination for Large-Factor Painting Super-Resolution

Image and Video Processing 2020-07-31 v4 Computer Vision and Pattern Recognition

Abstract

We aim to super-resolve digital paintings, synthesizing realistic details from high-resolution reference painting materials for very large scaling factors (e.g., 8X, 16X). However, previous single image super-resolution (SISR) methods would either lose textural details or introduce unpleasing artifacts. On the other hand, reference-based SR (Ref-SR) methods can transfer textures to some extent, but is still impractical to handle very large factors and keep fidelity with original input. To solve these problems, we propose an efficient high-resolution hallucination network for very large scaling factors with an efficient network structure and feature transferring. To transfer more detailed textures, we design a wavelet texture loss, which helps to enhance more high-frequency components. At the same time, to reduce the smoothing effect brought by the image reconstruction loss, we further relax the reconstruction constraint with a degradation loss which ensures the consistency between downscaled super-resolution results and low-resolution inputs. We also collected a high-resolution (e.g., 4K resolution) painting dataset PaintHD by considering both physical size and image resolution. We demonstrate the effectiveness of our method with extensive experiments on PaintHD by comparing with SISR and Ref-SR state-of-the-art methods.

Keywords

Cite

@article{arxiv.1912.00515,
  title  = {Texture Hallucination for Large-Factor Painting Super-Resolution},
  author = {Yulun Zhang and Zhifei Zhang and Stephen DiVerdi and Zhaowen Wang and Jose Echevarria and Yun Fu},
  journal= {arXiv preprint arXiv:1912.00515},
  year   = {2020}
}

Comments

Accepted to ECCV 2020. Supplementary material contains more visual results and is available at http://yulunzhang.com/papers/PaintingSR_supp_arXiv.pdf

R2 v1 2026-06-23T12:32:32.850Z