Related papers: CNSv2: Probabilistic Correspondence Encoded Neural…

Compressive sensing (CS), aiming to reconstruct an image/signal from a small set of random measurements has attracted considerable attentions in recent years. Due to the high dimensionality of images, previous CS methods mainly work on…

Visual servoing, the method of controlling robot motion through feedback from visual sensors, has seen significant advancements with the integration of optical flow-based methods. However, its application remains limited by inherent…

Classical structural-based visual localization methods offer high accuracy but face trade-offs in terms of storage, speed, and privacy. A recent innovation, keypoint scene coordinate regression (KSCR) named D2S addresses these issues by…

Deep Convolutional Neural Network (CNN) features have been demonstrated to be effective perceptual quality features. The perceptual loss, based on feature maps of pre-trained CNN's has proven to be remarkably effective for CNN based…

Finding a template in a search image is an important task underlying many computer vision applications. Recent approaches perform template matching in a deep feature-space, produced by a convolutional neural network (CNN), which is found to…

Semantic scene completion (SSC) has recently gained popularity because it can provide both semantic and geometric information that can be used directly for autonomous vehicle navigation. However, there are still challenges to overcome. SSC…

Establishing reliable image correspondences is essential for many robotic vision problems. However, existing methods often struggle in challenging scenarios with large viewpoint changes or textureless regions, where incorrect cor-…

We propose a novel learned keypoint detection method to increase the number of correct matches for the task of non-rigid image correspondence. By leveraging true correspondences acquired by matching annotated image pairs with a specified…

Convolutional neural networks (CNNs) are one of the most effective deep learning methods to solve image classification problems, but the best architecture of a CNN to solve a specific problem can be extremely complicated and hard to design.…

Dense image matching is a fundamental low-level problem in Computer Vision, which has received tremendous attention from both discrete and continuous optimization communities. The goal of this paper is to combine the advantages of discrete…

In the era of large foundation models, the quality of embeddings has become a central determinant of downstream task performance and overall system capability. Yet widely used dense embeddings are often extremely high-dimensional, incurring…

Deep learning based image compressed sensing (CS) has achieved great success. However, existing CS systems mainly adopt a fixed measurement matrix to images, ignoring the fact the optimal measurement numbers and bases are different for…

Convolutional Neural Networks (CNNs) have been successfully applied for relative camera pose estimation from labeled image-pair data, without requiring any hand-engineered features, camera intrinsic parameters or depth information. The…

Most recent work in goal oriented visual navigation resorts to large-scale machine learning in simulated environments. The main challenge lies in learning compact representations generalizable to unseen environments and in learning…

In this work we target the problem of estimating accurately localised correspondences between a pair of images. We adopt the recent Neighbourhood Consensus Networks that have demonstrated promising performance for difficult correspondence…

Semi-supervised semantic segmentation (SSS) aims at learning rich visual knowledge from cheap unlabeled images to enhance semantic segmentation capability. Among recent works, UniMatch improves its precedents tremendously by amplifying the…

Compression and reconstruction of visual data have been widely studied in the computer vision community, even before the popularization of deep learning. More recently, some have used deep learning to improve or refine existing pipelines,…

While neural symbolic methods demonstrate impressive performance in visual question answering on synthetic images, their performance suffers on real images. We identify that the long-tail distribution of visual concepts and unequal…

Neural video codecs have demonstrated great potential in video transmission and storage applications. Existing neural hybrid video coding approaches rely on optical flow or Gaussian-scale flow for prediction, which cannot support…

Correspondence matching is a fundamental problem in computer vision and robotics applications. Solving correspondence matching problems using neural networks has been on the rise recently. Rotation-equivariance and scale-equivariance are…