Related papers: FishEyeRecNet: A Multi-Context Collaborative Deep …

In many applications of deep learning, particularly those in image restoration, it is either very difficult, prohibitively expensive, or outright impossible to obtain paired training data precisely as in the real world. In such cases, one…

Underwater image enhancement is such an important low-level vision task with many applications that numerous algorithms have been proposed in recent years. These algorithms developed upon various assumptions demonstrate successes from…

Wide-angle portraits often enjoy expanded views. However, they contain perspective distortions, especially noticeable when capturing group portrait photos, where the background is skewed and faces are stretched. This paper introduces the…

In this paper, we deal with the problem of monocular depth estimation for fisheye cameras in a self-supervised manner. A known issue of self-supervised depth estimation is that it suffers in low-light/over-exposure conditions and in large…

Previous face inverse rendering methods often require synthetic data with ground truth and/or professional equipment like a lighting stage. However, a model trained on synthetic data or using pre-defined lighting priors is typically unable…

Deep neural networks demonstrate to have a high performance on image classification tasks while being more difficult to train. Due to the complexity and vanishing gradient problem, it normally takes a lot of time and more computational…

In the realm of digital media, the advent of AI-generated synthetic images has introduced significant challenges in distinguishing between real and fabricated visual content. These images, often indistinguishable from authentic ones, pose a…

This paper considers image change detection with only a small number of samples, which is a significant problem in terms of a few annotations available. A major impediment of image change detection task is the lack of large annotated…

In this paper, we present the first pinhole-fisheye framework for heterogeneous multi-view depth estimation, PFDepth. Our key insight is to exploit the complementary characteristics of pinhole and fisheye imagery (undistorted vs. distorted,…

Scene observation from multiple perspectives would bring a more comprehensive visual experience. However, in the context of acquiring multiple views in the dark, the highly correlated views are seriously alienated, making it challenging to…

Recovery of true color from underwater images is an ill-posed problem. This is because the wide-band attenuation coefficients for the RGB color channels depend on object range, reflectance, etc. which are difficult to model. Also, there is…

Deep learning methods have witnessed the great progress in image restoration with specific metrics (e.g., PSNR, SSIM). However, the perceptual quality of the restored image is relatively subjective, and it is necessary for users to control…

As a cornerstone technique for autonomous driving, Bird's Eye View (BEV) segmentation has recently achieved remarkable progress with pinhole cameras. However, it is non-trivial to extend the existing methods to fisheye cameras with severe…

Existing monocular 3D object detection methods have been demonstrated on rectilinear perspective images and fail in images with alternative projections such as those acquired by fisheye cameras. Previous works on object detection in fisheye…

In this work, we explore the technical feasibility of implementing end-to-end 3D object detection (3DOD) with surround-view fisheye camera system. Specifically, we first investigate the performance drop incurred when transferring classic…

Vessel segmentation of retinal images is a key diagnostic capability in ophthalmology. This problem faces several challenges including low contrast, variable vessel size and thickness, and presence of interfering pathology such as…

Advanced manipulation techniques have provided criminals with opportunities to make social panic or gain illicit profits through the generation of deceptive media, such as forged face images. In response, various deepfake detection methods…

The spread of deepfakes poses significant security concerns, demanding reliable detection methods. However, diverse generation techniques and class imbalance in datasets create challenges. We propose CAE-Net, a Convolution- and…

This research addresses the challenge of camera calibration and distortion parameter prediction from a single image using deep learning models. The main contributions of this work are: (1) demonstrating that a deep learning model, trained…

Lensless imaging has emerged as a potential solution towards realizing ultra-miniature cameras by eschewing the bulky lens in a traditional camera. Without a focusing lens, the lensless cameras rely on computational algorithms to recover…