# PRevivor: Reviving Ancient Chinese Paintings using Prior-Guided Color Transformers

arXiv: https://arxiv.org/abs/2511.01274 · HTML: https://mlsanity.com/paper/2511.01274/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 3 Nov 2025.

## Builds on (most cited first, 12 of 12)

- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [Bringing Old Photos Back to Life](https://mlsanity.com/paper/2004.09484/) (2020)
- [Colorization Transformer](https://mlsanity.com/paper/2102.04432/) (2021)
- [Instance-aware Image Colorization](https://mlsanity.com/paper/2005.10825/) (2020)
- [Deep Colorization](https://mlsanity.com/paper/1605.00075/) (2016)
- [ChromaGAN: Adversarial Picture Colorization with Semantic Class Distribution](https://mlsanity.com/paper/1907.09837/) (2019)
- [DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders](https://mlsanity.com/paper/2212.11613/) (2022)
- [BigColor: Colorization using a Generative Color Prior for Natural Images](https://mlsanity.com/paper/2207.09685/) (2022)
- [Control Color: Multimodal Diffusion-based Interactive Image Colorization](https://mlsanity.com/paper/2402.10855/) (2024)
- [Diffusing Colors: Image Colorization with Text Guided Diffusion](https://mlsanity.com/paper/2312.04145/) (2023)
- [Focusing on Persons: Colorizing Old Images Learning from Modern Historical Movies](https://mlsanity.com/paper/2108.06515/) (2021)
- [Multimodal Semantic-Aware Automatic Colorization with Diffusion Prior](https://mlsanity.com/paper/2404.16678/) (2024)

## Built on by (most cited first, 1 of 1)

- [Reviving Ancient Paintings via Poem: A Colorization Framework for Aligning Cultural Semantics](https://mlsanity.com/paper/2607.17638/) (2026)

## Abstract (arXiv)

Ancient Chinese paintings are a valuable cultural heritage that is damaged by irreversible color degradation. Reviving color-degraded paintings is extraordinarily difficult due to the complex chemistry mechanism. Progress is further slowed by the lack of comprehensive, high-quality datasets, which hampers the creation of end-to-end digital restoration tools. To revive colors, we propose PRevivor, a prior-guided color transformer that learns from recent paintings (e.g., Ming and Qing Dynasty) to restore ancient ones (e.g., Tang and Song Dynasty). To develop PRevivor, we decompose color restoration into two sequential sub-tasks: luminance enhancement and hue correction. For luminance enhancement, we employ two variational U-Nets and a multi-scale mapping module to translate faded luminance into restored counterparts. For hue correction, we design a dual-branch color query module guided by localized hue priors extracted from faded paintings. Specifically, one branch focuses attention on regions guided by masked priors, enforcing localized hue correction, whereas the other branch remains unconstrained to maintain a global reasoning capability. To evaluate PRevivor, we conduct extensive experiments against state-of-the-art colorization methods. The results demonstrate superior performance both quantitatively and qualitatively.