Research on Restoration of Murals Based on Diffusion Model and Transformer
Source abstract
Abstract
Due to the limitations of a priori knowledge and convolution operation, the existing image restoration techniques cannot be directly applied to the cultural relics mural restoration, in order to more accurately restore the or... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Digital Media and Visual Art
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (20)
Show source-provided references
1. Application of digital processing in relic image restoration design10.1007/s11220-019-0265-8 ↗
2. Deep learning algorithm in ancient relics image colour restoration technology10.1007/s11042-022-14108-z ↗
3. Generative adversarial nets10.1145/3422622 ↗
4. Attention is all you need
5. An image is worth 16 × 16 words: Transformers for image recognition at scale
6. A research review on deep learning based image restoration methods
7. Denoising diffusion probabilistic models
8. Repaint: Inpainting using denoising diffusion probabilistic models
9. Review of generating diffusion models
10. UNIT-DDPM: Unpaired image translation with denoising diffusion probabilistic models
11. All are worth words: A ViT backbone for diffusion models
12. Shift-Net: Image inpainting via deep feature rearrangement
13. Diffusion schrödinger bridge with applications to score-based generative modeling
14. StyleSwin: Transformer-based GAN for high-resolution image generation
15. Vector quantized diffusion model for text-to-image synthesis
16. Diffusion models beat gans on image synthesis
17. Y. T. Kang, “Image inpainting model based on gated deformable convolution and hierarchical transformer and its application,” Donghua Univ., Shanghai, China, 2023. doi: 10.27012/d.cnki.gdhuu.2022.001329.
18. Generative image inpainting with contextual attention
19. A mural restoration method combining global consistency and local continuity
20. PD-GAN: Probabilistic diverse GAN for image inpainting