Related papers: Aggregation of binary feature descriptors for comp…
The majority of approaches for acquiring dense 3D environment maps with RGB-D cameras assumes static environments or rejects moving objects as outliers. The representation and tracking of moving objects, however, has significant potential…
Recent approaches on visual scene understanding attempt to build a scene graph -- a computational representation of objects and their pairwise relationships. Such rich semantic representation is very appealing, yet difficult to obtain from…
Feature descriptors of point clouds are used in several applications, such as registration and part segmentation of 3D point clouds. Learning discriminative representations of local geometric features is unquestionably the most important…
We address the task of estimating camera parameters from a set of images depicting a scene. Popular feature-based structure-from-motion (SfM) tools solve this task by incremental reconstruction: they repeat triangulation of sparse 3D points…
Recent work on action recognition leverages 3D features and textual information to achieve state-of-the-art performance. However, most of the current few-shot action recognition methods still rely on 2D frame-level representations, often…
Representation of semantic context and local details is the essential issue for building modern semantic segmentation models. However, the interrelationship between semantic context and local details is not well explored in previous works.…
Keypoint detection and description is fundamental yet important in many vision applications. Most existing methods use detect-then-describe or detect-and-describe strategy to learn local features without considering their context…
In this study, we propose a novel scene descriptor for visual place recognition. Unlike popular bag-of-words scene descriptors which rely on a library of vector quantized visual features, our proposed descriptor is based on a library of raw…
Visual SLAM algorithms achieve significant improvements through the exploration of 3D Gaussian Splatting (3DGS) representations, particularly in generating high-fidelity dense maps. However, they depend on a static environment assumption…
In this paper, we present a monocular Simultaneous Localization and Mapping (SLAM) algorithm using high-level object and plane landmarks. The built map is denser, more compact and semantic meaningful compared to feature point based SLAM. We…
Place recognition is a core component of Simultaneous Localization and Mapping (SLAM) algorithms. Particularly in visual SLAM systems, previously-visited places are recognized by measuring the appearance similarity between images…
In this paper, we propose to augment image-based place recognition with structural cues. Specifically, these structural cues are obtained using structure-from-motion, such that no additional sensors are needed for place recognition. This is…
In recent years, coordinate-based neural implicit representations have shown promising results for the task of Simultaneous Localization and Mapping (SLAM). While achieving impressive performance on small synthetic scenes, these methods…
This paper introduces a state-of-the-art video representation and applies it to efficient action recognition and detection. We first propose to improve the popular dense trajectory features by explicit camera motion estimation. More…
Camera motion estimation is a key technique for 3D scene reconstruction and Simultaneous localization and mapping (SLAM). To make it be feasibly achieved, previous works usually assume slow camera motions, which limits its usage in many…
The bundle of geometry and appearance in computer vision has proven to be a promising solution for robots across a wide variety of applications. Stereo cameras and RGB-D sensors are widely used to realise fast 3D reconstruction and…
The ability to estimate rich geometry and camera motion from monocular imagery is fundamental to future interactive robotics and augmented reality applications. Different approaches have been proposed that vary in scene geometry…
The structure from motion (SfM) problem in computer vision is the problem of recovering the three-dimensional ($3$D) structure of a stationary scene from a set of projective measurements, represented as a collection of two-dimensional…
Camera localization methods based on retrieval, local feature matching, and 3D structure-based pose estimation are accurate but require high storage, are slow, and are not privacy-preserving. A method based on scene landmark detection (SLD)…
In this paper, we present a decision level fused local Morphological Pattern Spectrum(PS) and Local Binary Pattern (LBP) approach for an efficient shape representation and classification. This method makes use of Earth Movers Distance(EMD)…