English
Related papers

Related papers: Physically-admissible polarimetric data augmentati…

200 papers

Image-to-image translation is a new field in computer vision with multiple potential applications in the medical domain. However, for supervised image translation frameworks, co-registered datasets, paired in a pixel-wise sense, are…

Computer Vision and Pattern Recognition · Computer Science 2021-02-02 Karim Armanious , Chenming Jiang , Sherif Abdulatif , Thomas Küstner , Sergios Gatidis , Bin Yang

This year alone has seen unprecedented leaps in the area of learning-based image translation, namely CycleGAN, by Zhu et al. But experiments so far have been tailored to merely two domains at a time, and scaling them to more would require…

Computer Vision and Pattern Recognition · Computer Science 2017-12-20 Asha Anoosheh , Eirikur Agustsson , Radu Timofte , Luc Van Gool

We propose a novel framework for controllable pathological image synthesis for data augmentation. Inspired by CycleGAN, we perform cycle-consistent image-to-image translation between two domains: healthy and pathological. Guided by a…

Image and Video Processing · Electrical Eng. & Systems 2021-01-19 Khrystyna Faryna , Kevin Koschmieder , Marcella M. Paul , Thomas van den Heuvel , Anke van der Eerden , Rashindra Manniesing , Bram van Ginneken

The recent direction of unpaired image-to-image translation is on one hand very exciting as it alleviates the big burden in obtaining label-intensive pixel-to-pixel supervision, but it is on the other hand not fully satisfactory due to the…

Computer Vision and Pattern Recognition · Computer Science 2019-02-27 Rui Zhang , Tomas Pfister , Jia Li

Little publicly available data exists for polarimetric measurements. When designing task specific polarimetric systems, the statistical properties of the task specific data becomes important. Until better polarimetric datasets are available…

Instrumentation and Detectors · Physics 2017-07-11 Israel J. Vaughn , Andrey S. Alenin , J. Scott Tyo

Despite recent success in conditional image synthesis, prevalent input conditions such as semantics and edges are not clear enough to express `Linear (Ridges)' and `Planar (Scale)' representations. To address this problem, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2022-05-16 Gunhee Lee , Jonghwa Yim , Chanran Kim , Minjae Kim

Polarization information of the light can provide rich cues for computer vision and scene understanding tasks, such as the type of material, pose, and shape of the objects. With the advent of new and cheap polarimetric sensors, this imaging…

Computer Vision and Pattern Recognition · Computer Science 2024-01-03 Joaquin Rodriguez , Lew-Fock-Chong Lew-Yan-Voon , Renato Martins , Olivier Morel

The challenge of image-based 3D reconstruction for glossy objects lies in separating diffuse and specular components on glossy surfaces from captured images, a task complicated by the ambiguity in discerning lighting conditions and material…

Computer Vision and Pattern Recognition · Computer Science 2025-04-10 Bojian Wu , Yifan Peng , Ruizhen Hu , Xiaowei Zhou

Ultrasound is the second most used modality in medical imaging. It is cost effective, hazardless, portable and implemented routinely in numerous clinical procedures. Nonetheless, image quality is characterized by granulated appearance, poor…

Image and Video Processing · Electrical Eng. & Systems 2022-06-13 Lilach Barkat , Moti Freiman , Haim Azhari

CT is commonly used in orthopedic procedures. MRI is used along with CT to identify muscle structures and diagnose osteonecrosis due to its superior soft tissue contrast. However, MRI has poor contrast for bone structures. Clearly, it would…

Computer Vision and Pattern Recognition · Computer Science 2018-08-01 Yuta Hiasa , Yoshito Otake , Masaki Takao , Takumi Matsuoka , Kazuma Takashima , Jerry L. Prince , Nobuhiko Sugano , Yoshinobu Sato

This paper presents Fd-CycleGAN, an image-to-image (I2I) translation framework that enhances latent representation learning to approximate real data distributions. Building upon the foundation of CycleGAN, our approach integrates Local…

Computer Vision and Pattern Recognition · Computer Science 2025-08-06 Shivangi Nigam , Adarsh Prasad Behera , Shekhar Verma , P. Nagabhushan

Light emitted from a source into a scene can undergo complex interactions with scene surfaces of different material types before being reflected. During this transport, every surface reflection is encoded in the properties of the photons…

Computer Vision and Pattern Recognition · Computer Science 2021-09-16 Seung-Hwan Baek , Felix Heide

Successive image generation using cyclic transformations is demonstrated by extending the CycleGAN model to transform images among three different categories. Repeated application of the trained generators produces sequences of images that…

Computer Vision and Pattern Recognition · Computer Science 2025-01-07 Takaya Tanaka , Yutaka Yamaguti

One of the main factors that contributed to the large advances in autonomous driving is the advent of deep learning. For safer self-driving vehicles, one of the problems that has yet to be solved completely is lane detection. Since methods…

Computer Vision and Pattern Recognition · Computer Science 2020-07-15 Lucas Tabelini , Rodrigo Berriel , Thiago M. Paixão , Claudine Badue , Alberto F. De Souza , Thiago Oliveira-Santos

Image datasets are essential not only in validating existing methods in computer vision but also in developing new methods. Most existing image datasets focus on trichromatic intensity images to mimic human vision. However, polarization and…

Computer Vision and Pattern Recognition · Computer Science 2023-12-01 Yujin Jeon , Eunsue Choi , Youngchan Kim , Yunseong Moon , Khalid Omer , Felix Heide , Seung-Hwan Baek

Lightweight deep learning models offer substantial reductions in computational cost and environmental impact, making them crucial for scientific applications. We present a lightweight CycleGAN for modality transfer in fluorescence…

Computer Vision and Pattern Recognition · Computer Science 2025-10-20 Mohammad Soltaninezhad , Yashar Rouzbahani , Jhonatan Contreras , Rohan Chippalkatti , Daniel Kwaku Abankwa , Christian Eggeling , Thomas Bocklitz

A major challenge in applying deep learning to medical imaging is the paucity of annotated data. This study demonstrates that synthetic colonoscopy images generated by Generative Adversarial Network (GAN) inversion can be used as training…

Image and Video Processing · Electrical Eng. & Systems 2025-07-02 Mayank Golhar , Taylor L. Bobrow , Saowanee Ngamruengphong , Nicholas J. Durr

Accurate segmentation of floating debris on water is often compromised by surface glare and changing outdoor illumination. Polarimetric imaging offers a single-sensor route to mitigate water-surface glare that disrupts semantic segmentation…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Luis F. W. Batista , Tom Bourbon , Cedric Pradalier

Virtual Human Simulation has been widely used for different purposes, such as comfort or accessibility analysis. In this paper, we investigate the possibility of using this type of technique to extend the training datasets of pedestrians to…

Computer Vision and Pattern Recognition · Computer Science 2019-05-02 Marcelo C. Ghilardi , Leandro Dihl , Estevão Testa , Pedro Braga , João P. Pianta , Isabel H. Manssour , Soraia R. Musse

Although training data is essential for machine learning, railway companies are facing difficulties in gathering adequate images of defective equipment due to their proactive replacement of would be defective equipment. Nevertheless,…

Computer Vision and Pattern Recognition · Computer Science 2021-02-26 Takuro Hoshi , Yohei Baba , Gaurang Gavai