Related papers: EPI-based Oriented Relation Networks for Light Fie…

The deep-learning based image matching networks can now handle significantly larger variations in viewpoints and illuminations while providing matched pairs of pixels with sub-pixel precision. These networks have been trained with…

Recently, learning-based ego-motion estimation approaches have drawn strong interest from studies mostly focusing on visual perception. These groundbreaking works focus on unsupervised learning for odometry estimation but mostly for visual…

Echo Planar Imaging (EPI) is widely used for its rapid acquisition but suffers from severe geometric distortions due to B0 inhomogeneities, particularly along the phase encoding direction. Existing methods follow a two-step process:…

While conventional depth estimation can infer the geometry of a scene from a single RGB image, it fails to estimate scene regions that are occluded by foreground objects. This limits the use of depth prediction in augmented and virtual…

Omnidirectional image (ODI) data is captured with a 360x180 field-of-view, which is much wider than the pinhole cameras and contains richer spatial information than the conventional planar images. Accordingly, omnidirectional vision has…

Depth map estimation is a crucial task in computer vision, and new approaches have recently emerged taking advantage of light fields, as this new imaging modality captures much more information about the angular direction of light rays…

We propose a novel DNN based framework called the Enhanced Correlation Matching based Video Frame Interpolation Network to support high resolution like 4K, which has a large scale of motion and occlusion. Considering the extensibility of…

The challenge of object categorization in images is largely due to arbitrary translations and scales of the foreground objects. To attack this difficulty, we propose a new approach called collaborative receptive field learning to extract…

Computing the epipolar geometry from feature points between cameras with very different viewpoints is often error prone, as an object's appearance can vary greatly between images. For such cases, it has been shown that using motion…

Light field imaging has recently known a regain of interest due to the availability of practical light field capturing systems that offer a wide range of applications in the field of computer vision. However, capturing high-resolution light…

Environment perception, including object detection and distance estimation, is one of the most crucial tasks for autonomous driving. Many attentions have been paid on the object detection task, but distance estimation only arouse few…

Self-supervised learning of depth and ego-motion from unlabeled monocular video has acquired promising results and drawn extensive attention. Most existing methods jointly train the depth and pose networks by photometric consistency of…

Monocular depth estimation is an especially important task in robotics and autonomous driving, where 3D structural information is essential. However, extreme lighting conditions and complex surface objects make it difficult to predict depth…

Keypoint matching can be slow and unreliable in challenging conditions such as repetitive textures or wide-baseline views. In such cases, known geometric relations (e.g., the fundamental matrix) can be used to restrict potential…

Learning neural implicit fields of 3D shapes is a rapidly emerging field that enables shape representation at arbitrary resolutions. Due to the flexibility, neural implicit fields have succeeded in many research areas, including shape…

Omnidirectional image (ODI) data is captured with a field-of-view of 360x180, which is much wider than the pinhole cameras and captures richer surrounding environment details than the conventional perspective images. In recent years, the…

Oblique plane microscopy (OPM) is a single objective light-sheet microscopy which performs three dimensional (3D) imaging by axial scan of the generated light-sheet. Recently, multiple techniques for lateral scan of the generated…

Detection of objects is extremely important in various aerial vision-based applications. Over the last few years, the methods based on convolution neural networks have made substantial progress. However, because of the large variety of…

Deep learning models have witnessed depth and pose estimation framework on unannotated datasets as a effective pathway to succeed in endoscopic navigation. Most current techniques are dedicated to developing more advanced neural networks to…

We present three multi-scale similarity learning architectures, or DeepSim networks. These models learn pixel-level matching with a contrastive loss and are agnostic to the geometry of the considered scene. We establish a middle ground…