Despite advancements in SLAM technologies, robust operation under challenging conditions such as low-texture, motion-blur, or challenging lighting remains an open challenge. Such conditions are common in applications such as assistive navigation for the visually impaired. These challenges undermine localization accuracy and tracking stability, reducing navigation reliability and safety. To overcome these limitations, we present SELM-SLAM3, a deep learning-enhanced visual SLAM framework that integrates SuperPoint and LightGlue for robust feature extraction and matching. We evaluated our framework using TUM RGB-D, ICL-NUIM, and TartanAir datasets, which feature diverse and challenging scenarios. SELM-SLAM3 outperforms conventional ORB-SLAM3 by an average of 87.84% and exceeds state-of-the-art RGB-D SLAM systems by 36.77%. Our framework demonstrates enhanced performance under challenging conditions, such as low-texture scenes and fast motion, providing a reliable platform for developing navigation aids for the visually impaired.

Matching local visual features is a crucial problem in computer vision and its accuracy greatly depends on the choice of similarity measure. As it is generally very difficult to design by hand a similarity or a kernel perfectly adapted to the data of interest, learning it automatically with as few assumptions as possible is preferable. However, available techniques for kernel learning suffer from several limitations, such as restrictive parametrization or scalability. In this paper, we introduce a simple and flexible family of non-linear kernels which we refer to as Quantized Kernels (QK). QKs are arbitrary kernels in the index space of a data quantizer, i.e., piecewise constant similarities in the original feature space. Quantization allows to compress features and keep the learning tractable. As a result, we obtain state-of-the-art matching performance on a standard benchmark dataset with just a few bits to represent each feature dimension. QKs also have explicit non-linear, low-dimensional feature mappings that grant access to Euclidean geometry for uncompressed features.

-- Robust and efficient local feature matching plays a crucial role in applications such as SLAM and visual localization for robotics. Despite great progress, it is still very challenging to extract robust and discriminative visual features in scenarios with drastic lighting changes, low texture areas, or repetitive patterns. In this paper, we propose a new lightweight network called LiftF eat, which lifts the robustness of raw descriptor by aggregating 3D geometric feature. Specifically, we first adopt a pre-trained monocular depth estimation model to generate pseudo surface normal label, supervising the extraction of 3D geometric feature in terms of predicted surface normal. Integrating such 3D geometric feature enhances the discriminative ability of 2D feature description in extreme conditions. Extensive experimental results on relative pose estimation, homography estimation, and visual localization tasks, demonstrate that our LiftFeat outperforms some lightweight state-of-the-art methods. I. INTRODUCTION Local feature matching between images is critical for many core robotic tasks, including Structure from Motion (SfM) [1], [2], [3], Simultaneous Localization and Mapping (SLAM) [4], [5], [6], [7], and visual localization [8], [9], [10], [11]. In practical applications, there are some scenes with extreme conditions, such as significant variation of illumination, and the presence of textureless or repetitive patterns.

Rapid generation of large-scale orthoimages from Unmanned Aerial Vehicles (UAVs) has been a long-standing focus of research in the field of aerial mapping. A multi-sensor UAV system, integrating the Global Positioning System (GPS), Inertial Measurement Unit (IMU), 4D millimeter-wave radar and camera, can provide an effective solution to this problem. In this paper, we utilize multi-sensor data to overcome the limitations of conventional orthoimage generation methods in terms of temporal performance, system robustness, and geographic reference accuracy. A prior-pose-optimized feature matching method is introduced to enhance matching speed and accuracy, reducing the number of required features and providing precise references for the Structure from Motion (SfM) process. The proposed method exhibits robustness in low-texture scenes like farmlands, where feature matching is difficult. Experiments show that our approach achieves accurate feature matching orthoimage generation in a short time. The proposed drone system effectively aids in farmland detection and management.

In this paper, we study how to synthesize a dynamic reference from an external dictionary to perform conditional coding of the input image in the latent domain and how to learn the conditional latent synthesis and coding modules in an end-to-end manner. Our approach begins by constructing a universal image feature dictionary using a multi-stage approach involving modified spatial pyramid pooling, dimension reduction, and multi-scale feature clustering. For each input image, we learn to synthesize a conditioning latent by selecting and synthesizing relevant features from the dictionary, which significantly enhances the model's capability in capturing and exploring image source correlation. This conditional latent synthesis involves a correlation-based feature matching and alignment strategy, comprising a Conditional Latent Matching (CLM) module and a Conditional Latent Synthesis (CLS) module. The synthesized latent is then used to guide the encoding process, allowing for more efficient compression by exploiting the correlation between the input image and the reference dictionary. According to our theoretical analysis, the proposed conditional latent coding (CLC) method is robust to perturbations in the external dictionary samples and the selected conditioning latent, with an error bound that scales logarithmically with the dictionary size, ensuring stability even with large and diverse dictionaries. Experimental results on benchmark datasets show that our new method improves the coding performance by a large margin (up to 1.2 dB) with a very small overhead of approximately 0.5\% bits per pixel. Our code is publicly available at https://github.com/ydchen0806/CLC.

Matching local visual features is a crucial problem in computer vision and its accuracy greatly depends on the choice of similarity measure. As it is generally very difficult to design by hand a similarity or a kernel perfectly adapted to the data of interest, learning it automatically with as few assumptions as possible is preferable. However, available techniques for kernel learning suffer from several limitations, such as restrictive parametrization or scalability. In this paper, we introduce a simple and flexible family of non-linear kernels which we refer to as Quantized Kernels (QK). QKs are arbitrary kernels in the index space of a data quantizer, i.e., piecewise constant similarities in the original feature space.

We are interested in long-term deployments of autonomous robots to aid astronauts with maintenance and monitoring operations in settings such as the International Space Station. Unfortunately, such environments tend to be highly dynamic and unstructured, and their frequent reconfiguration poses a challenge for robust long-term localization of robots. Many state-of-the-art visual feature-based localization algorithms are not robust towards spatial scene changes, and SLAM algorithms, while promising, cannot run within the low-compute budget available to space robots. To address this gap, we present a computationally efficient semantic masking approach for visual feature matching that improves the accuracy and robustness of visual localization systems during long-term deployment in changing environments. Our method introduces a lightweight check that enforces matches to be within long-term static objects and have consistent semantic classes. We evaluate this approach using both map-based relocalization and relative pose estimation and show that it improves Absolute Trajectory Error (ATE) and correct match ratios on the publicly available Astrobee dataset. While this approach was originally developed for microgravity robotic freeflyers, it can be applied to any visual feature matching pipeline to improve robustness.

Event cameras, with high temporal resolution and high dynamic range, have limited research on the inter-modality local feature extraction and matching of event-image data. We propose EI-Nexus, an unmediated and flexible framework that integrates two modality-specific keypoint extractors and a feature matcher. To achieve keypoint extraction across viewpoint and modality changes, we bring Local Feature Distillation (LFD), which transfers the viewpoint consistency from a well-learned image extractor to the event extractor, ensuring robust feature correspondence. Furthermore, with the help of Context Aggregation (CA), a remarkable enhancement is observed in feature matching. We further establish the first two inter-modality feature matching benchmarks, MVSEC-RPE and EC-RPE, to assess relative pose estimation on event-image data. Our approach outperforms traditional methods that rely on explicit modal transformation, offering more unmediated and adaptable feature extraction and matching, achieving better keypoint similarity and state-of-the-art results on the MVSEC-RPE and EC-RPE benchmarks. The source code and benchmarks will be made publicly available at https://github.com/ZhonghuaYi/EI-Nexus_official.

The evolving field of mobile robotics has indeed increased the demand for simultaneous localization and mapping (SLAM) systems. To augment the localization accuracy and mapping efficacy of SLAM, we refined the core module of the SLAM system. Within the feature matching phase, we introduced cross-validation matching to filter out mismatches. In the keyframe selection strategy, an exponential threshold function is constructed to quantify the keyframe selection process. Compared with a single robot, the multi-robot collaborative SLAM (CSLAM) system substantially improves task execution efficiency and robustness. By employing a centralized structure, we formulate a multi-robot SLAM system and design a coarse-to-fine matching approach for multi-map point cloud registration. Our system, built upon ORB-SLAM3, underwent extensive evaluation utilizing the TUM RGB-D, EuRoC MAV, and TUM_VI datasets. The experimental results demonstrate a significant improvement in the positioning accuracy and mapping quality of our enhanced algorithm compared to those of ORB-SLAM3, with a 12.90% reduction in the absolute trajectory error.

Numerous navigation applications rely on data from global navigation satellite systems (GNSS), even though their accuracy is compromised in urban areas, posing a significant challenge, particularly for precise autonomous car localization. Extensive research has focused on enhancing localization accuracy by integrating various sensor types to address this issue. This paper introduces a novel approach for car localization, leveraging image features that correspond with highly detailed semantic 3D building models. The core concept involves augmenting positioning accuracy by incorporating prior geometric and semantic knowledge into calculations. The work assesses outcomes using Level of Detail 2 (LoD2) and Level of Detail 3 (LoD3) models, analyzing whether facade-enriched models yield superior accuracy. This comprehensive analysis encompasses diverse methods, including off-the-shelf feature matching and deep learning, facilitating thorough discussion. Our experiments corroborate that LoD3 enables detecting up to 69\% more features than using LoD2 models. We believe that this study will contribute to the research of enhancing positioning accuracy in GNSS-denied urban canyons. It also shows a practical application of under-explored LoD3 building models on map-based car positioning.