# WavePaint: Resource-efficient Token-mixer for Self-supervised Inpainting

arXiv: https://arxiv.org/abs/2307.00407 · HTML: https://mlsanity.com/paper/2307.00407/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 49 references that are in the map.
- First posted on arXiv 1 Jul 2023.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [MetaFormer Is Actually What You Need for Vision](https://mlsanity.com/paper/2111.11418/) (2021)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Large Scale Image Completion via Co-Modulated Generative Adversarial Networks](https://mlsanity.com/paper/2103.10428/) (2021)
- [MAT: Mask-Aware Transformer for Large Hole Image Inpainting](https://mlsanity.com/paper/2203.15270/) (2022)
- [Patches Are All You Need?](https://mlsanity.com/paper/2201.09792/) (2022)
- [EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning](https://mlsanity.com/paper/1901.00212/) (2019)
- [Semantic Image Inpainting with Deep Generative Models](https://mlsanity.com/paper/1607.07539/) (2016)
- [High-Fidelity Pluralistic Image Completion with Transformers](https://mlsanity.com/paper/2103.14031/) (2021)
- [Improving Generalization Performance by Switching from Adam to SGD](https://mlsanity.com/paper/1712.07628/) (2017)
- [Recurrent Feature Reasoning for Image Inpainting](https://mlsanity.com/paper/2008.03737/) (2020)
- [Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations](https://mlsanity.com/paper/2007.06929/) (2020)
- [Aggregated Contextual Transformations for High-Resolution Image Inpainting](https://mlsanity.com/paper/2104.01431/) (2021)
- [The Limitations of Adversarial Training and the Blind-Spot Attack](https://mlsanity.com/paper/1901.04684/) (2019)
- [SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting](https://mlsanity.com/paper/1805.03356/) (2018)
- [WaveFill: A Wavelet-based Generation Network for Image Inpainting](https://mlsanity.com/paper/2107.11027/) (2021)
- [Image Inpainting by End-to-End Cascaded Refinement with Mask Awareness](https://mlsanity.com/paper/2104.13743/) (2021)
- [WaveMix: A Resource-efficient Neural Network for Image Analysis](https://mlsanity.com/paper/2205.14375/) (2022)

## Built on by (most cited first, 2 of 2)

- [The Brittleness of AI-Generated Image Watermarking Techniques: Examining Their Robustness Against Visual Paraphrasing Attacks](https://mlsanity.com/paper/2408.10446/) (2024)
- [CoIn: Comprehensive 2D-3D Inpainting with Gaussian Splatting Guidance](https://mlsanity.com/paper/2606.27584/) (2026)

## Abstract (arXiv)

Image inpainting, which refers to the synthesis of missing regions in an image, can help restore occluded or degraded areas and also serve as a precursor task for self-supervision. The current state-of-the-art models for image inpainting are computationally heavy as they are based on transformer or CNN backbones that are trained in adversarial or diffusion settings. This paper diverges from vision transformers by using a computationally-efficient WaveMix-based fully convolutional architecture -- WavePaint. It uses a 2D-discrete wavelet transform (DWT) for spatial and multi-resolution token-mixing along with convolutional layers. The proposed model outperforms the current state-of-the-art models for image inpainting on reconstruction quality while also using less than half the parameter count and considerably lower training and evaluation times. Our model even outperforms current GAN-based architectures in CelebA-HQ dataset without using an adversarially trainable discriminator. Our work suggests that neural architectures that are modeled after natural image priors require fewer parameters and computations to achieve generalization comparable to transformers.