Related papers: Depth Estimation Algorithm Based on Transformer-En…
The Mean Square Error (MSE) has shown its strength when applied in deep generative models such as Auto-Encoders to model reconstruction loss. However, in image domain especially, the limitation of MSE is obvious: it assumes pixel…
Since context modeling is critical for estimating depth from a single image, researchers put tremendous effort into obtaining global context. Many global manipulations are designed for traditional CNN-based architectures to overcome the…
A novel multi-focus image fusion algorithm performed in spatial domain based on similarity characteristics is proposed incorporating with region segmentation. In this paper, a new similarity measure is developed based on the structural…
Acquiring accurate three-dimensional depth information conventionally requires expensive multibeam LiDAR devices. Recently, researchers have developed a less expensive option by predicting depth information from two-dimensional color…
Monocular depth estimation (MDE) plays a pivotal role in various computer vision applications, such as robotics, augmented reality, and autonomous driving. Despite recent advancements, existing methods often fail to meet key requirements…
Depth estimation is a fundamental knowledge for autonomous systems that need to assess their own state and perceive the surrounding environment. Deep learning algorithms for depth estimation have gained significant interest in recent years,…
Recent advances in end-to-end unsupervised learning has significantly improved the performance of monocular depth prediction and alleviated the requirement of ground truth depth. Although a plethora of work has been done in enforcing…
Deploying depth estimation networks in the real world requires high-level robustness against various adverse conditions to ensure safe and reliable autonomy. For this purpose, many autonomous vehicles employ multi-modal sensor systems,…
The advent of autonomous driving and advanced driver assistance systems necessitates continuous developments in computer vision for 3D scene understanding. Self-supervised monocular depth estimation, a method for pixel-wise distance…
Local feature matching between images remains a challenging task, especially in the presence of significant appearance variations, e.g., extreme viewpoint changes. In this work, we propose DeepMatcher, a deep Transformer-based network built…
Volumetric depth map fusion based on truncated signed distance functions has become a standard method and is used in many 3D reconstruction pipelines. In this paper, we are generalizing this classic method in multiple ways: 1) Semantics:…
Depth completion aims to recover dense depth maps from sparse depth measurements. It is of increasing importance for autonomous driving and draws increasing attention from the vision community. Most of existing methods directly train a…
Removing noise from images is a challenging and fundamental problem in the field of computer vision. Images captured by modern cameras are inevitably degraded by noise which limits the accuracy of any quantitative measurements on those…
This paper aims to address the problem of supervised monocular depth estimation. We start with a meticulous pilot study to demonstrate that the long-range correlation is essential for accurate depth estimation. Therefore, we propose to…
Given sparse depths and the corresponding RGB images, depth completion aims at spatially propagating the sparse measurements throughout the whole image to get a dense depth prediction. Despite the tremendous progress of deep-learning-based…
Monocular Depth Estimation (MDE) is a fundamental computer vision task with important applications in 3D vision. The current mainstream MDE methods employ an encoder-decoder architecture with multi-level/scale feature processing. However,…
Transparent objects are widely used in industrial automation and daily life. However, robust visual recognition and perception of transparent objects have always been a major challenge. Currently, most commercial-grade depth cameras are…
Natural signals and images are well-known to be approximately sparse in transform domains such as Wavelets and DCT. This property has been heavily exploited in various applications in image processing and medical imaging. Compressed sensing…
Image fusion is a technique to integrate information from multiple source images with complementary information to improve the richness of a single image. Due to insufficient task-specific training data and corresponding ground truth, most…
Self-supervised methods have showed promising results on depth estimation task. However, previous methods estimate the target depth map and camera ego-motion simultaneously, underusing multi-frame correlation information and ignoring the…