# Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation

arXiv: https://arxiv.org/abs/1711.09554 · HTML: https://mlsanity.com/paper/1711.09554/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2017.

## Built on by (most cited first, 8 of 8)

- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [Dual Contrastive Learning for Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2104.07689/) (2021)
- [Semi-supervised reference-based sketch extraction using a contrastive learning framework](https://mlsanity.com/paper/2407.14026/) (2024)
- [Deformation-aware GAN for Medical Image Synthesis with Substantially Misaligned Pairs](https://mlsanity.com/paper/2408.09432/) (2024)
- [Keypoint-Guided Optimal Transport: Models, Algorithms, and Applications](https://mlsanity.com/paper/2303.13102/) (2023)
- [Image-to-Image Translation Framework Embedded with Rotation Symmetry Priors](https://mlsanity.com/paper/2604.12805/) (2026)
- [Membership Privacy Protection for Image Translation Models via Adversarial Knowledge Distillation](https://mlsanity.com/paper/2203.05212/) (2022)
- [Capabilities, Limitations and Challenges of Style Transfer with CycleGANs: A Study on Automatic Ring Design Generation](https://mlsanity.com/paper/2207.08989/) (2022)

## Abstract (arXiv)

Image-to-image translation has been made much progress with embracing Generative Adversarial Networks (GANs). However, it's still very challenging for translation tasks that require high quality, especially at high-resolution and photorealism. In this paper, we present Discriminative Region Proposal Adversarial Networks (DRPAN) for high-quality image-to-image translation. We decompose the procedure of image-to-image translation task into three iterated steps, first is to generate an image with global structure but some local artifacts (via GAN), second is using our DRPnet to propose the most fake region from the generated image, and third is to implement "image inpainting" on the most fake region for more realistic result through a reviser, so that the system (DRPAN) can be gradually optimized to synthesize images with more attention on the most artifact local part. Experiments on a variety of image-to-image translation tasks and datasets validate that our method outperforms state-of-the-arts for producing high-quality translation results in terms of both human perceptual studies and automatic quantitative measures.