Related papers: Learning to Segment Dynamic Objects using SLAM Out…

Existence of symmetric objects, whose observation at different viewpoints can be identical, can deteriorate the performance of simultaneous localization and mapping(SLAM). This work proposes a system for robustly optimizing the pose of…

Understanding the surrounding environment is fundamental in autonomous driving and robotic perception. Distinguishing between known classes and previously unseen objects is crucial in real-world environments, as done in Anomaly…

Object-level SLAM offers structured and semantically meaningful environment representations, making it more interpretable and suitable for high-level robotic tasks. However, most existing approaches rely on RGB-D sensors or monocular views,…

We present a novel approach to unsupervised learning for video object segmentation (VOS). Unlike previous work, our formulation allows to learn dense feature representations directly in a fully convolutional regime. We rely on uniform grid…

Deep learning has enabled remarkable advances in scene understanding, particularly in semantic segmentation tasks. Yet, current state of the art approaches are limited to a closed set of classes, and fail when facing novel elements, also…

Significant strides have been made using large vision-language models, like Stable Diffusion (SD), for a variety of downstream tasks, including image editing, image correspondence, and 3D shape generation. Inspired by these advancements, we…

SLAM is an important capability for many autonomous systems, and modern LiDAR-based methods offer promising performance. However, for long duration missions, existing works that either operate directly the full pointclouds or on extracted…

Conventional self-supervised monocular depth prediction methods are based on a static environment assumption, which leads to accuracy degradation in dynamic scenes due to the mismatch and occlusion problems introduced by object motions.…

This paper addresses the task of segmenting moving objects in unconstrained videos. We introduce a novel two-stream neural network with an explicit memory module to achieve this. The two streams of the network encode spatial and temporal…

Monocular SLAM algorithms perform robustly when observing rigid scenes, however, they fail when the observed scene deforms, for example, in medical endoscopy applications. We present DefSLAM, the first monocular SLAM capable of operating in…

Monocular visual odometry is a key technology in various autonomous systems. Traditional feature-based methods suffer from failures due to poor lighting, insufficient texture, and large motions. In contrast, recent learning-based dense SLAM…

Learning a data-driven spatio-temporal semantic representation of the objects is the key to coherent and consistent labelling in video. This paper proposes to achieve semantic video object segmentation by learning a data-driven…

Estimating depth from RGB images can facilitate many computer vision tasks, such as indoor localization, height estimation, and simultaneous localization and mapping (SLAM). Recently, monocular depth estimation has obtained great progress…

Self-supervised monocular depth estimation approaches either ignore independently moving objects in the scene or need a separate segmentation step to identify them. We propose MonoDepthSeg to jointly estimate depth and segment moving…

Although instance-aware perception is a key prerequisite for many autonomous robotic applications, most of the methods only partially solve the problem by focusing solely on known object categories. However, for robots interacting in…

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…

2D LiDAR SLAM (Simultaneous Localization and Mapping) is widely used in indoor environments due to its stability and flexibility. However, its mapping procedure is usually operated by a joystick in static environments, while indoor…

Progress in self-supervised learning has brought strong general image representation learning methods. Yet so far, it has mostly focused on image-level learning. In turn, tasks such as unsupervised image segmentation have not benefited from…

We propose a Spatiotemporal Sampling Network (STSN) that uses deformable convolutions across time for object detection in videos. Our STSN performs object detection in a video frame by learning to spatially sample features from the adjacent…

Event cameras offer advantages in object detection tasks due to high-speed response, low latency, and robustness to motion blur. However, event cameras lack texture and color information, making open-vocabulary detection particularly…