# Boundary-aware Decoupled Flow Networks for Realistic Extreme Rescaling

arXiv: https://arxiv.org/abs/2405.02941 · HTML: https://mlsanity.com/paper/2405.02941/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 5 May 2024.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020)
- [Residual Attention Network for Image Classification](https://mlsanity.com/paper/1704.06904/) (2017)
- [Invertible Residual Networks](https://mlsanity.com/paper/1811.00995/) (2018)
- [MambaIR: A Simple Baseline for Image Restoration with State-Space Model](https://mlsanity.com/paper/2402.15648/) (2024)
- [GAN Prior Embedded Network for Blind Face Restoration in the Wild](https://mlsanity.com/paper/2105.06070/) (2021)
- [GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution](https://mlsanity.com/paper/2012.00739/) (2020)
- [Invertible Image Rescaling](https://mlsanity.com/paper/2005.05650/) (2020)
- [Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling](https://mlsanity.com/paper/2108.05301/) (2021)
- [Backdoor Defense via Adaptively Splitting Poisoned Dataset](https://mlsanity.com/paper/2303.12993/) (2023)
- [HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention](https://mlsanity.com/paper/2404.06351/) (2024)
- [FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs](https://mlsanity.com/paper/2403.13507/) (2024)
- [Contrastive Masked Autoencoders for Self-Supervised Video Hashing](https://mlsanity.com/paper/2211.11210/) (2022)
- [Are Deep Neural Architectures Losing Information? Invertibility Is Indispensable](https://mlsanity.com/paper/2009.03173/) (2020)

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

- [Timestep-Aware Diffusion Model for Extreme Image Rescaling](https://mlsanity.com/paper/2408.09151/) (2024)

## Abstract (arXiv)

Recently developed generative methods, including invertible rescaling network (IRN) based and generative adversarial network (GAN) based methods, have demonstrated exceptional performance in image rescaling. However, IRN-based methods tend to produce over-smoothed results, while GAN-based methods easily generate fake details, which thus hinders their real applications. To address this issue, we propose Boundary-aware Decoupled Flow Networks (BDFlow) to generate realistic and visually pleasing results. Unlike previous methods that model high-frequency information as standard Gaussian distribution directly, our BDFlow first decouples the high-frequency information into textitsemantic high-frequency that adheres to a Boundary distribution and textitnon-semantic high-frequency counterpart that adheres to a Gaussian distribution. Specifically, to capture semantic high-frequency parts accurately, we use Boundary-aware Mask (BAM) to constrain the model to produce rich textures, while non-semantic high-frequency part is randomly sampled from a Gaussian distribution.Comprehensive experiments demonstrate that our BDFlow significantly outperforms other state-of-the-art methods while maintaining lower complexity. Notably, our BDFlow improves the PSNR by 4.4 dB and the SSIM by 0.1 on average over GRAIN, utilizing only 74% of the parameters and 20% of the computation. The code will be available at https://github.com/THU-Kingmin/BAFlow.