Related papers: DERD-Net: Learning Depth from Event-based Ray Dens…

Event cameras provide a number of benefits over traditional cameras, such as the ability to track incredibly fast motions, high dynamic range, and low power consumption. However, their application into computer vision problems, many of…

Depth estimation is a fundamental task in 3D geometry. While stereo depth estimation can be achieved through triangulation methods, it is not as straightforward for monocular methods, which require the integration of global and local…

Current self-supervised methods for monocular depth estimation are largely based on deeply nested convolutional networks that leverage stereo image pairs or monocular sequences during a training phase. However, they often exhibit inaccurate…

Event cameras are neuromorphically inspired sensors that sparsely and asynchronously report brightness changes. Their unique characteristics of high temporal resolution, high dynamic range, and low power consumption make them well-suited…

Event cameras are bio-inspired, motion-activated sensors that demonstrate substantial potential in handling challenging situations, such as motion blur and high-dynamic range. In this paper, we proposed EVI-SAM to tackle the problem of 6…

We propose an extension to the segment-based global localization method for LiDAR SLAM using descriptors learned considering the visual context of the segments. A new architecture of the deep neural network is presented that learns the…

The existence of variable factors within the environment can cause a decline in camera localization accuracy, as it violates the fundamental assumption of a static environment in Simultaneous Localization and Mapping (SLAM) algorithms.…

Most SLAM algorithms are based on the assumption that the scene is static. However, in practice, most scenes are dynamic which usually contains moving objects, these methods are not suitable. In this paper, we introduce DymSLAM, a dynamic…

We present DropD-SLAM, a real-time monocular SLAM system that achieves RGB-D-level accuracy without relying on depth sensors. The system replaces active depth input with three pretrained vision modules: a monocular metric depth estimator, a…

In this letter, we present a neural field-based real-time monocular mapping framework for accurate and dense Simultaneous Localization and Mapping (SLAM). Recent neural mapping frameworks show promising results, but rely on RGB-D or pose…

Monocular SLAM has received a lot of attention due to its simple RGB inputs and the lifting of complex sensor constraints. However, existing monocular SLAM systems are designed for bounded scenes, restricting the applicability of SLAM…

Event cameras are dynamic vision sensors inspired by the biological retina, characterized by their high dynamic range, high temporal resolution, and low power consumption. These features make them capable of perceiving 3D environments even…

Event cameras are rapidly emerging as powerful vision sensors for 3D reconstruction, uniquely capable of asynchronously capturing per-pixel brightness changes. Compared to traditional frame-based cameras, event cameras produce sparse yet…

Event cameras capture sparse, high-temporal-resolution visual information, making them particularly suitable for challenging environments with high-speed motion and strongly varying lighting conditions. However, the lack of large datasets…

Learning-based stereo matching has recently achieved promising results, yet still suffers difficulties in establishing reliable matches in weakly matchable regions that are textureless, non-Lambertian, or occluded. In this paper, we address…

With extremely high temporal resolution, event cameras have a large potential for robotics and computer vision. However, their asynchronous imaging mechanism often aggravates the measurement sensitivity to noises and brings a physical…

We present three multi-scale similarity learning architectures, or DeepSim networks. These models learn pixel-level matching with a contrastive loss and are agnostic to the geometry of the considered scene. We establish a middle ground…

Existing simultaneous localization and mapping (SLAM) algorithms are not robust in challenging low-texture environments because there are only few salient features. The resulting sparse or semi-dense map also conveys little information for…

Emerging 3D scene representations, such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), have demonstrated their effectiveness in Simultaneous Localization and Mapping (SLAM) for photo-realistic rendering, particularly…

Neural implicit scene representations have recently shown promising results in dense visual SLAM. However, existing implicit SLAM algorithms are constrained to single-agent scenarios, and fall difficulties in large-scale scenes and long…