Texture Hallucination for Large-Scale Painting Super-Resolution

12/01/2019
by   Yulun Zhang, et al.
11

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 scales and keep fidelity with original input. To solve these problems, we propose an efficient high-resolution hallucination network for very large scaling factors with 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.

READ FULL TEXT

page 1

page 5

page 7

page 8

research
04/10/2018

Reference-Conditioned Super-Resolution by Neural Texture Transfer

With the recent advancement in deep learning, we have witnessed a great ...
research
03/26/2021

Super-Resolving Compressed Video in Coding Chain

Scaling and lossy coding are widely used in video transmission and stora...
research
06/02/2023

A Feature Reuse Framework with Texture-adaptive Aggregation for Reference-based Super-Resolution

Reference-based super-resolution (RefSR) has gained considerable success...
research
06/07/2020

Learning Texture Transformer Network for Image Super-Resolution

We study on image super-resolution (SR), which aims to recover realistic...
research
07/15/2019

Boosting Resolution and Recovering Texture of micro-CT Images with Deep Learning

Digital Rock Imaging is constrained by detector hardware, and a trade-of...
research
05/14/2021

A Frequency Domain Constraint for Synthetic X-ray Image Super Resolution

Synthetic X-ray images can be helpful for image guiding systems and VR s...
research
06/03/2021

Robust Reference-based Super-Resolution via C2-Matching

Reference-based Super-Resolution (Ref-SR) has recently emerged as a prom...

Please sign up or login with your details

Forgot password? Click here to reset