Applications of Deep Learning for Top-View Omnidirectional Imaging: A Survey

Yu, Jingrui; Grassi, Ana Cecilia Perez; Hirtz, Gangolf

doi:10.1109/cvprw59228.2023.00683

Cited by 5 publications

(1 citation statement)

References 93 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep neural networks can learn complex mappings between distorted and undistorted images, enabling them to effectively address the challenges posed by fisheye distortions. Specifically, DL models have shown great promise in distortion correction and super-resolution tasks, which aim to recover high-resolution details from lowresolution images [17].…”

Section: Introductionmentioning

confidence: 99%

Distortion-aware super-resolution for planetary exploration images

Landro,

Gallo,

Pelosi

et al. 2024

Sixteenth International Conference on Machine Vision (ICMV 2023)

View full text Add to dashboard Cite

Super-resolution is crucial in computer vision and digital image processing, aiming to enhance low-quality images' resolution and visual quality. This paper focuses on correcting the distortion introduced by fisheye lenses and improving the resolution of images for better detail representation. Specifically, we propose an evaluation approach that benchmarks three state-of-the-art models in different categories: Real-ESRGAN (convolutions), SwinIR (transformers), and SR3 (diffusion). We evaluate their performance in super-resolution and distortion correction tasks using metrics such as PSNR and SSIM. To facilitate this evaluation, we create and release a new dataset of lunar surface images with fisheye distortion applied. Our experiments demonstrate the effectiveness of each model in handling distortion and improving image resolution. The results show that large models generally outperform medium models, and PSNR models achieve higher PSNR and SSIM scores than GAN models. Additionally, we evaluate the distortion correction by comparing the corrected images with ground truth. Our findings contribute to understanding different model categories and their performance in super-resolution and distortion correction tasks. The proposed dataset and evaluation approach can be valuable resources for future research.

show abstract

Section: Introductionmentioning

confidence: 99%