Related papers: T2Net: Synthetic-to-Realistic Translation for Solv…

Image-to-Image (I2I) translation is a heated topic in academia, and it also has been applied in real-world industry for tasks like image synthesis, super-resolution, and colorization. However, traditional I2I translation methods train data…

Eye image segmentation is a critical step in eye tracking that has great influence over the final gaze estimate. Segmentation models trained using supervised machine learning can excel at this task, their effectiveness is determined by the…

Despite that the performance of image-to-image translation has been significantly improved by recent progress in generative models, current methods still suffer from severe degradation in training stability and sample quality when applied…

Data-driven paradigms using machine learning are becoming ubiquitous in image processing and communications. In particular, image-to-image (I2I) translation is a generic and widely used approach to image processing problems, such as image…

Existing methods for stereo work on narrow baseline image pairs giving limited performance between wide baseline views. This paper proposes a framework to learn and estimate dense stereo for people from wide baseline image pairs. A…

Recently, deep-networks-based hashing (deep hashing) has become a leading approach for large-scale image retrieval. It aims to learn a compact bitwise representation for images via deep networks, so that similar images are mapped to nearby…

Generative adversarial networks has emerged as a defacto standard for image translation problems. To successfully drive such models, one has to rely on additional networks e.g., discriminators and/or perceptual networks. Training these…

Autonomous navigation in underwater environments presents challenges due to factors such as light absorption and water turbidity, limiting the effectiveness of optical sensors. Sonar systems are commonly used for perception in underwater…

Image translation with convolutional neural networks has recently been used as an approach to multimodal change detection. Existing approaches train the networks by exploiting supervised information of the change areas, which, however, is…

Images captured by fisheye lenses violate the pinhole camera assumption and suffer from distortions. Rectification of fisheye images is therefore a crucial preprocessing step for many computer vision applications. In this paper, we propose…

Multimodal machine translation (MMT) simultaneously takes the source sentence and a relevant image as input for translation. Since there is no paired image available for the input sentence in most cases, recent studies suggest utilizing…

This paper develops a unified framework for image-to-image translation based on conditional diffusion models and evaluates this framework on four challenging image-to-image translation tasks, namely colorization, inpainting, uncropping, and…

Scene depth estimation from stereo and monocular imagery is critical for extracting 3D information for downstream tasks such as scene understanding. Recently, learning-based methods for depth estimation have received much attention due to…

Most deep models for underwater image enhancement resort to training on synthetic datasets based on underwater image formation models. Although promising performances have been achieved, they are still limited by two problems: (1) existing…

Stereo vision is an effective technique for depth estimation with broad applicability in autonomous urban and highway driving. While various deep learning-based approaches have been developed for stereo, the input data from a binocular…

The task of single image super-resolution (SISR) aims at reconstructing a high-resolution (HR) image from a low-resolution (LR) image. Although significant progress has been made by deep learning models, they are trained on synthetic paired…

Supervised learning methods to infer (hypothesize) depth of a scene from a single image require costly per-pixel ground-truth. We follow a geometric approach that exploits abundant stereo imagery to learn a model to hypothesize scene…

Underwater image enhancement (UIE) is vital for high-level vision-related underwater tasks. Although learning-based UIE methods have made remarkable achievements in recent years, it's still challenging for them to consistently deal with…

The image-to-image translation is a learning task to establish a visual mapping between an input and output image. The task has several variations differentiated based on the purpose of the translation, such as synthetic to real…

Compositing is one of the most common operations in photo editing. To generate realistic composites, the appearances of foreground and background need to be adjusted to make them compatible. Previous approaches to harmonize composites have…