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

MAKE IMPACT

Shangrong Yang , Chunyu Lin , Kang Liao , Yao Zhao · YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2301.11785

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.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2301.11785

PDF

https://arxiv.org/pdf/2301.11785

OA Status

green

Cited By

2

Related Works

10

OpenAlex ID

https://openalex.org/W4318621121

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4318621121

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2301.11785

Digital Object Identifier

Title

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

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2023

Year of publication

Publication date

2023-01-26

Full publication date if available

Authors

Shangrong Yang, Chunyu Lin, Kang Liao, Yao Zhao

List of authors in order

Landing page

https://arxiv.org/abs/2301.11785

Publisher landing page

PDF URL

https://arxiv.org/pdf/2301.11785

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2301.11785

Direct OA link when available

Concepts

Generalization, Artificial intelligence, Computer science, Rectification, Synthetic data, Computer vision, Image (mathematics), Distortion (music), Pyramid (geometry), Pattern recognition (psychology), Mathematics, Amplifier, Computer network, Power (physics), Physics, Bandwidth (computing), Quantum mechanics, Geometry, Mathematical analysis

Top concepts (fields/topics) attached by OpenAlex

Cited by

2

Total citation count in OpenAlex

Citations by year (recent)

2024: 2

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload