Single-image reflection removal : from computational imaging to deep learning

Deep-learning (DL)-based methods are of growing importance in the field of single image super-resolution (SISR). The practical application of these DL-based models is a remaining problem due to the requirement of heavy computation and huge storage resources. The powerful feature maps of hidden layers in convolutional neural networks (CNN) help the model learn useful information. However, there exists redundancy among feature maps, which can be further exploited. To address these issues, this paper proposes a lightweight efficient feature generating network (EFGN) for SISR by constructing the efficient feature generating block (EFGB). Specifically, the EFGB can conduct plain operations on the original features to produce more feature maps with parameters slightly increasing. With the help of these extra feature maps, the network can extract more useful information from low resolution (LR) images to reconstruct the desired high resolution (HR) images. Experiments conducted on the benchmark datasets demonstrate that the proposed EFGN can outperform other deep-learning based methods in most cases and possess relatively lower model complexity. Additionally, the running time measurement indicates the feasibility of real-time monitoring.

Download Full-text

Deep learning-based single image face depth data enhancement

Computer Vision and Image Understanding ◽

10.1016/j.cviu.2021.103247 ◽

2021 ◽

pp. 103247

Author(s):

Torsten Schlett ◽

Christian Rathgeb ◽

Christoph Busch

Keyword(s):

Deep Learning ◽

Single Image ◽

Depth Data

Download Full-text

Three-Dimensional Shape Reconstruction from a Single Image by Deep Learning

International Journal of Advanced Computer Science and Applications ◽

10.14569/ijacsa.2020.0110245 ◽

2020 ◽

Vol 11 (2) ◽

Author(s):

Kentaro Sakai ◽

Yoshiaki Yasumura

Keyword(s):

Deep Learning ◽

Three Dimensional ◽

Shape Reconstruction ◽

Single Image ◽

Dimensional Shape ◽

Three Dimensional Shape

Download Full-text

Light People: Professor Aydogan Ozcan

Light Science & Applications ◽

10.1038/s41377-021-00643-1 ◽

2021 ◽

Vol 10 (1) ◽

Author(s):

Tingting Sun

Keyword(s):

Deep Learning ◽

Los Angeles ◽

Learning Algorithm ◽

Computational Imaging ◽

Technological Innovations ◽

Image Generation ◽

Sensing Technology ◽

Reconstruction Methods ◽

New Ideas ◽

The University

EditorialIn 2016, the news that Google’s artificial intelligence (AI) robot AlphaGo, based on the principle of deep learning, won the victory over lee Sedol, the former world Go champion and the famous 9th Dan competitor of Korea, caused a sensation in both fields of AI and Go, which brought epoch-making significance to the development of deep learning. Deep learning is a complex machine learning algorithm that uses multiple layers of artificial neural networks to automatically analyze signals or data. At present, deep learning has penetrated into our daily life, such as the applications of face recognition and speech recognition. Scientists have also made many remarkable achievements based on deep learning. Professor Aydogan Ozcan from the University of California, Los Angeles (UCLA) led his team to research deep learning algorithms, which provided new ideas for the exploring of optical computational imaging and sensing technology, and introduced image generation and reconstruction methods which brought major technological innovations to the development of related fields. Optical designs and devices are moving from being physically driven to being data-driven. We are much honored to have Aydogan Ozcan, Fellow of the National Academy of Inventors and Chancellor’s Professor of UCLA, to unscramble his latest scientific research results and foresight for the future development of related fields, and to share his journey of pursuing Optics, his indissoluble relationship with Light: Science & Applications (LSA), and his experience in talent cultivation.

Download Full-text

DEEP LEARNING FOR MONOCULAR DEPTH ESTIMATION FROM UAV IMAGES

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-annals-v-2-2020-451-2020 ◽

2020 ◽

Vol V-2-2020 ◽

pp. 451-458

Author(s):

L. Madhuanand ◽

F. Nex ◽

M. Y. Yang

Keyword(s):

Deep Learning ◽

Ground Level ◽

Depth Estimation ◽

Aerial Images ◽

Aerial Image ◽

Depth Information ◽

Single Image ◽

Monocular Depth ◽

Uav Images ◽

Image Depth

Abstract. Depth is an essential component for various scene understanding tasks and for reconstructing the 3D geometry of the scene. Estimating depth from stereo images requires multiple views of the same scene to be captured which is often not possible when exploring new environments with a UAV. To overcome this monocular depth estimation has been a topic of interest with the recent advancements in computer vision and deep learning techniques. This research has been widely focused on indoor scenes or outdoor scenes captured at ground level. Single image depth estimation from aerial images has been limited due to additional complexities arising from increased camera distance, wider area coverage with lots of occlusions. A new aerial image dataset is prepared specifically for this purpose combining Unmanned Aerial Vehicles (UAV) images covering different regions, features and point of views. The single image depth estimation is based on image reconstruction techniques which uses stereo images for learning to estimate depth from single images. Among the various available models for ground-level single image depth estimation, two models, 1) a Convolutional Neural Network (CNN) and 2) a Generative Adversarial model (GAN) are used to learn depth from aerial images from UAVs. These models generate pixel-wise disparity images which could be converted into depth information. The generated disparity maps from these models are evaluated for its internal quality using various error metrics. The results show higher disparity ranges with smoother images generated by CNN model and sharper images with lesser disparity range generated by GAN model. The produced disparity images are converted to depth information and compared with point clouds obtained using Pix4D. It is found that the CNN model performs better than GAN and produces depth similar to that of Pix4D. This comparison helps in streamlining the efforts to produce depth from a single aerial image.

Download Full-text

AtLoc: Attention Guided Camera Localization

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i06.6608 ◽

2020 ◽

Vol 34 (06) ◽

pp. 10393-10401

Author(s):

Bing Wang ◽

Changhao Chen ◽

Chris Xiaoxuan Lu ◽

Peijun Zhao ◽

Niki Trigoni ◽

...

Keyword(s):

Deep Learning ◽

Experimental Evidence ◽

State Of The Art ◽

Source Code ◽

Single Image ◽

Saliency Maps ◽

Camera Localization ◽

Camera Pose ◽

Dynamic Objects ◽

Indoor And Outdoor

Deep learning has achieved impressive results in camera localization, but current single-image techniques typically suffer from a lack of robustness, leading to large outliers. To some extent, this has been tackled by sequential (multi-images) or geometry constraint approaches, which can learn to reject dynamic objects and illumination conditions to achieve better performance. In this work, we show that attention can be used to force the network to focus on more geometrically robust objects and features, achieving state-of-the-art performance in common benchmark, even if using only a single image as input. Extensive experimental evidence is provided through public indoor and outdoor datasets. Through visualization of the saliency maps, we demonstrate how the network learns to reject dynamic objects, yielding superior global camera pose regression performance. The source code is avaliable at https://github.com/BingCS/AtLoc.

Download Full-text