Related papers: SimVODIS: Simultaneous Visual Odometry, Object Det…
We study lifelong visual perception in an embodied setup, where we develop new models and compare various agents that navigate in buildings and occasionally request annotations which, in turn, are used to refine their visual perception…
Visual-Inertial Odometry (VIO) usually suffers from drifting over long-time runs, the accuracy is easily affected by dynamic objects. We propose DynaVIG, a navigation and object tracking system based on the integration of Monocular Vision,…
Current simultaneous localization and mapping (SLAM) algorithms perform well in static environments but easily fail in dynamic environments. Recent works introduce deep learning-based semantic information to SLAM systems to reduce the…
Video Object Segmentation, and video processing in general, has been historically dominated by methods that rely on the temporal consistency and redundancy in consecutive video frames. When the temporal smoothness is suddenly broken, such…
Interactive segmentation aims to accurately segment target objects with minimal user interactions. However, current methods often fail to accurately separate target objects from the background, due to a limited understanding of order, the…
Recently, Space-Time Memory Network (STM) based methods have achieved state-of-the-art performance in semi-supervised video object segmentation (VOS). A crucial problem in this task is how to model the dependency both among different frames…
LiDAR is crucial for robust 3D scene perception in autonomous driving. LiDAR perception has the largest body of literature after camera perception. However, multi-task learning across tasks like detection, segmentation, and motion…
A self-driving vehicle (SDV) must be able to perceive its surroundings and predict the future behavior of other traffic participants. Existing works either perform object detection followed by trajectory forecasting of the detected objects,…
What is a good visual representation for autonomous agents? We address this question in the context of semantic visual navigation, which is the problem of a robot finding its way through a complex environment to a target object, e.g. go to…
Visual Odometry (VO) is a method to estimate self-motion of a mobile robot using visual sensors. Unlike odometry based on integrating differential measurements that can accumulate errors, such as inertial sensors or wheel encoders, visual…
Building vehicles capable of operating without human supervision requires the determination of the agent's pose. Visual Odometry (VO) algorithms estimate the egomotion using only visual changes from the input images. The most recent VO…
Independently exploring unknown spaces or finding objects in an indoor environment is a daily but challenging task for visually impaired people. However, common 2D assistive systems lack depth relationships between various objects,…
We propose to jointly learn multi-view geometry and warping between views of the same object instances for robust cross-view object detection. What makes multi-view object instance detection difficult are strong changes in viewpoint,…
Robust geometric and semantic scene understanding is ever more important in many real-world applications such as autonomous driving and robotic navigation. In this paper, we propose a multi-task learning-based approach capable of jointly…
With the rapid development of intelligent transportation system applications, a tremendous amount of multi-view video data has emerged to enhance vehicle perception. However, performing video analytics efficiently by exploiting the…
As robotics continues to advance, the need for adaptive and continuously-learning embodied agents increases, particularly in the realm of assistance robotics. Quick adaptability and long-term information retention are essential to operate…
The ability to detect and track objects in the visual world is a crucial skill for any intelligent agent, as it is a necessary precursor to any object-level reasoning process. Moreover, it is important that agents learn to track objects…
Predicting future sensory states is crucial for learning agents such as robots, drones, and autonomous vehicles. In this paper, we couple multiple sensory modalities with exploratory actions and propose a predictive neural network…
Collaborative SLAM enables a group of agents to simultaneously co-localize and jointly map an environment, thus paving the way to wide-ranging applications of multi-robot perception and multi-user AR experiences by eliminating the need for…
Passive visual systems typically fail to recognize objects in the amodal setting where they are heavily occluded. In contrast, humans and other embodied agents have the ability to move in the environment, and actively control the viewing…