Related papers: Data Efficient Visual Place Recognition Using Extr…
Visual Place Recognition (VPR) requires robust retrieval of geotagged images despite large appearance, viewpoint, and environmental variation. Prior methods focus on descriptor fine-tuning or fixed sampling strategies yet neglect the…
Visual Place Recognition (VPR) is critical for autonomous navigation, yet state-of-the-art methods lack well-calibrated uncertainty estimation. Standard pipelines cannot reliably signal when a query is ambiguous or a match is likely…
LiDAR-based place recognition (LPR) plays a pivotal role in autonomous driving, which assists Simultaneous Localization and Mapping (SLAM) systems in reducing accumulated errors and achieving reliable localization. However, existing reviews…
Human visual scene understanding is so remarkable that we are able to recognize a revisited place when entering it from the opposite direction it was first visited, even in the presence of extreme variations in appearance. This capability…
Efficient point cloud coding has become increasingly critical for multiple applications such as virtual reality, autonomous driving, and digital twin systems, where rich and interactive 3D data representations may functionally make the…
Recently, the methods based on Convolutional Neural Networks (CNNs) have gained popularity in the field of visual place recognition (VPR). In particular, the features from the middle layers of CNNs are more robust to drastic appearance…
Camera sensors have been widely used in intelligent robotic systems. Developing camera sensors with high sensing efficiency has always been important to reduce the power, memory, and other related resources. Inspired by recent success on…
Visual Place Recognition and Visual Localization are essential components in navigation and mapping for autonomous vehicles especially in GNSS-denied navigation scenarios. Recent work has focused on ground or close to ground applications…
Existing visual place recognition (VPR) datasets predominantly rely on vehicle-mounted imagery, offer limited multimodal diversity, and underrepresent dense pedestrian street scenes, particularly in non-Western urban contexts. We introduce…
Mapping is crucial in robotics for localization and downstream decision-making. As robots are deployed in ever-broader settings, the maps they rely on continue to increase in size. However, storing these maps indefinitely (cold storage),…
Compared with raw images, the more common JPEG images are less useful for machine vision algorithms and professional photographers because JPEG-sRGB does not preserve a linear relation between pixel values and the light measured from the…
In recent years, much research has been conducted on image super-resolution (SR). To the best of our knowledge, however, few SR methods were concerned with compressed images. The SR of compressed images is a challenging task due to the…
Due to the increasing requirements for transmission of images in computer, mobile environments, the research in the field of image compression has increased significantly. Image compression plays a crucial role in digital image processing,…
Absolute Pose Regression (APR) predicts 6D camera poses but lacks the adaptability to unknown environments without retraining, while Relative Pose Regression (RPR) generalizes better yet requires a large image retrieval database. Visual…
Video representation learning is an increasingly important topic in machine learning research. We present Video JEPA with Variance-Covariance Regularization (VJ-VCR): a joint-embedding predictive architecture for self-supervised video…
Empirical evidence has demonstrated that learning-based image compression can outperform classical compression frameworks. This has led to the ongoing standardization of learned-based image codecs, namely Joint Photographic Experts Group…
Deep neural networks are powerful, yet their high complexity greatly limits their potential to be deployed on billions of resource-constrained edge devices. Pruning is a crucial network compression technique, yet most existing methods focus…
Deep learning model inference on embedded devices is challenging due to the limited availability of computation resources. A popular alternative is to perform model inference on the cloud, which requires transmitting images from the…
Visual Odometry (VO) accumulates a positional drift in long-term robot navigation tasks. Although Convolutional Neural Networks (CNNs) improve VO in various aspects, VO still suffers from moving obstacles, discontinuous observation of…
After the incredible success of deep learning in the computer vision domain, there has been much interest in applying Convolutional Network (ConvNet) features in robotic fields such as visual navigation and SLAM. Unfortunately, there are…