Related papers: Matching entropy based disparity estimation from l…

Accurately extracting patterns that appear frequently only within specific time intervals, together with their dense intervals, is important in many applications such as understanding seasonal demand and detecting anomalous…

Robust three-dimensional scene understanding is now an ever-growing area of research highly relevant in many real-world applications such as autonomous driving and robotic navigation. In this paper, we propose a multi-task learning-based…

Incorporating feature selection into a classification or regression method often carries a number of advantages. In this paper we formalize feature selection specifically from a discriminative perspective of improving…

Dense matching is crucial for 3D scene reconstruction since it enables the recovery of scene 3D geometry from image acquisition. Deep Learning (DL)-based methods have shown effectiveness in the special case of epipolar stereo disparity…

We study discrete dynamics governed by a difference inclusion whose increment is the sum of a selection from a set-valued map and a noise term. For any bounded realization, convergence follows once the inter-iterate diameter is controlled…

This paper establishes an information theoretic framework for deep metric based image registration techniques. We show an exact equivalence between maximum profile likelihood and minimization of joint entropy, an important early information…

Due to its capability to identify erroneous disparity assignments in dense stereo matching, confidence estimation is beneficial for a wide range of applications, e.g. autonomous driving, which needs a high degree of confidence as mandatory…

The study of approximate matching in the Massively Parallel Computations (MPC) model has recently seen a burst of breakthroughs. Despite this progress, however, we still have a far more limited understanding of maximal matching which is one…

This paper investigates how to step up local image descriptor matching by exploiting matching context information. Two main contexts are identified, originated respectively from the descriptor space and from the keypoint space. The former…

Current feature matching methods prioritize improving modeling capabilities to better align outputs with ground-truth matches, which are the theoretical upper bound on matching results, metaphorically depicted as the "ceiling". However,…

Window decoding, first proposed to reduce decoding complexity for real-time decoding, is an essential component to realize scalable, universal-fault tolerant computation. Prior work has focused on improving throughput through…

Data augmentation is crucial for improving the robustness of face detection systems, especially under challenging conditions such as occlusion, illumination variation, and complex environments. Traditional copy paste augmentation often…

Low-contrast image enhancement is essential for high-quality image display and other visual applications. However, it is a challenging task as the enhancement is expected to increase the visibility of an image while maintaining its…

Depth completion, aiming to predict dense depth maps from sparse depth measurements, plays a crucial role in many computer vision related applications. Deep learning approaches have demonstrated overwhelming success in this task. However,…

Estimation of optical aberrations from volumetric intensity images is a key step in sensorless adaptive optics for 3D microscopy. Recent approaches based on deep learning promise accurate results at fast processing speeds. However,…

Local feature matching is an essential component in many visual applications. In this work, we propose OAMatcher, a Tranformer-based detector-free method that imitates humans behavior to generate dense and accurate matches. Firstly,…

Hierarchical beam search in mmWave communications incurs substantial training overhead, necessitating deep learning-enabled beam predictions to effectively leverage channel priors and mitigate this overhead. In this study, we introduce a…

This work delves into unsupervised monocular depth estimation in endoscopy, which leverages adjacent frames to establish a supervisory signal during the training phase. For many clinical applications, e.g., surgical navigation, temporally…

Recent advances in deep-learning based methods for image matching have demonstrated their superiority over traditional algorithms, enabling correspondence estimation in challenging scenes with significant differences in viewing angles,…

Depth estimation is a fundamental problem in light field processing. Epipolar-plane image (EPI)-based methods often encounter challenges such as low accuracy in slope computation due to discretization errors and limited angular resolution.…