# Dual Diffusion Architecture for Fisheye Image Rectification: Synthetic-to-Real Generalization

arXiv: https://arxiv.org/abs/2301.11785 · HTML: https://mlsanity.com/paper/2301.11785/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 23 of its 51 references that are in the map.
- First posted on arXiv 26 Jan 2023.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 23 of 23)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [WaveGrad: Estimating Gradients for Waveform Generation](https://mlsanity.com/paper/2009.00713/) (2020)
- [Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction](https://mlsanity.com/paper/2002.11927/) (2020)
- [Deblurring via Stochastic Refinement](https://mlsanity.com/paper/2112.02475/) (2021)
- [WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving](https://mlsanity.com/paper/1905.01489/) (2019)
- [Semantic Image Synthesis via Diffusion Models](https://mlsanity.com/paper/2207.00050/) (2022)
- [WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis](https://mlsanity.com/paper/2106.09660/) (2021)
- [Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Model](https://mlsanity.com/paper/2208.07791/) (2022)
- [Target-Aware Deep Tracking](https://mlsanity.com/paper/1904.01772/) (2019)
- [FishEyeRecNet: A Multi-Context Collaborative Deep Network for Fisheye Image Rectification](https://mlsanity.com/paper/1804.04784/) (2018)
- [Blind Geometric Distortion Correction on Images Through Deep Learning](https://mlsanity.com/paper/1909.03459/) (2019)
- [Learning to Calibrate Straight Lines for Fisheye Image Rectification](https://mlsanity.com/paper/1904.09856/) (2019)
- [Progressively Complementary Network for Fisheye Image Rectification Using Appearance Flow](https://mlsanity.com/paper/2103.16026/) (2021)

## Built on by (most cited first, 5 of 5)

- [Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement](https://mlsanity.com/paper/2311.16495/) (2023)
- [Minimalist and High-Quality Panoramic Imaging with PSF-aware Transformers](https://mlsanity.com/paper/2306.12992/) (2023)
- [DarSwin: Distortion Aware Radial Swin Transformer](https://mlsanity.com/paper/2304.09691/) (2023)
- [DarSwin-Unet: Distortion Aware Encoder-Decoder Architecture](https://mlsanity.com/paper/2407.17328/) (2024)
- [QueryCDR: Query-Based Controllable Distortion Rectification Network for Fisheye Images](https://mlsanity.com/paper/2412.13496/) (2024)

## Abstract (arXiv)

Fisheye image rectification has a long-term unresolved issue with synthetic-to-real generalization. In most previous works, the model trained on the synthetic images obtains unsatisfactory performance on the real-world fisheye image. To this end, we propose a Dual Diffusion Architecture (DDA) for the fisheye rectification with a better generalization ability. The proposed DDA is simultaneously trained with paired synthetic fisheye images and unlabeled real fisheye images. By gradually introducing noises, the synthetic and real fisheye images can eventually develop into a consistent noise distribution, improving the generalization and achieving unlabeled real fisheye correction. The original image serves as the prior guidance in existing DDPMs (Denoising Diffusion Probabilistic Models). However, the non-negligible indeterminate relationship between the prior condition and the target affects the generation performance. Especially in the rectification task, the radial distortion can cause significant artifacts. Therefore, we provide an unsupervised one-pass network that produces a plausible new condition to strengthen guidance. This network can be regarded as an alternate scheme for fast producing reliable results without iterative inference. Compared with the state-of-the-art methods, our approach can reach superior performance in both synthetic and real fisheye image corrections.