Related papers: Self-Supervised Deep Visual Odometry with Online A…
We tackle the task of semi-supervised video object segmentation, i.e. segmenting the pixels belonging to an object in the video using the ground truth pixel mask for the first frame. We build on the recently introduced one-shot video object…
Humans and animals can learn complex predictive models that allow them to accurately and reliably reason about real-world phenomena, and they can adapt such models extremely quickly in the face of unexpected changes. Deep neural network…
This paper studies monocular visual odometry (VO) problem. Most of existing VO algorithms are developed under a standard pipeline including feature extraction, feature matching, motion estimation, local optimisation, etc. Although some of…
In this work we present WGANVO, a Deep Learning based monocular Visual Odometry method. In particular, a neural network is trained to regress a pose estimate from an image pair. The training is performed using a semi-supervised approach.…
Estimating relative camera poses from consecutive frames is a fundamental problem in visual odometry (VO) and simultaneous localization and mapping (SLAM), where classic methods consisting of hand-crafted features and sampling-based outlier…
We present READMem (Robust Embedding Association for a Diverse Memory), a modular framework for semi-automatic video object segmentation (sVOS) methods designed to handle unconstrained videos. Contemporary sVOS works typically aggregate…
In this paper, we present iDVO (inertia-embedded deep visual odometry), a self-supervised learning based monocular visual odometry (VO) for road vehicles. When modelling the geometric consistency within adjacent frames, most deep VO methods…
Video Anomaly Detection (VAD) identifies unusual activities in video streams, a key technology with broad applications ranging from surveillance to healthcare. Tackling VAD in real-life settings poses significant challenges due to the…
Under certain statistical assumptions of noise, recent self-supervised approaches for denoising have been introduced to learn network parameters without true clean images, and these methods can restore an image by exploiting information…
Visual-based localization has made significant progress, yet its performance often drops in large-scale, outdoor, and long-term settings due to factors like lighting changes, dynamic scenes, and low-texture areas. These challenges degrade…
Vision-and-language navigation (VLN) is a challenging task that requires an agent to navigate in real-world environments by understanding natural language instructions and visual information received in real-time. Prior works have…
Resource-constrained autonomous robots rely on sparse direct and semi-direct visual-(inertial)-odometry (VO) pipelines, as they provide a favorable tradeoff between accuracy, robustness, and computational cost. However, the performance of…
Visual Odometry (VO) is used in many applications including robotics and autonomous systems. However, traditional approaches based on feature matching are computationally expensive and do not directly address failure cases, instead relying…
Drawing inspiration from gradient-based meta-learning methods with infinitely small gradient steps, we introduce Continuous-Time Meta-Learning (COMLN), a meta-learning algorithm where adaptation follows the dynamics of a gradient vector…
In recent years, deep neural networks have shown remarkable progress in dense disparity estimation from dynamic scenes in monocular structured light systems. However, their performance significantly drops when applied in unseen…
Most learning-based methods estimate ego-motion by utilizing visual sensors, which suffer from dramatic lighting variations and textureless scenarios. In this paper, we incorporate sparse but accurate depth measurements obtained from lidars…
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…
Recent learning-based LiDAR odometry methods have demonstrated their competitiveness. However, most methods still face two substantial challenges: 1) the 2D projection representation of LiDAR data cannot effectively encode 3D structures…
We propose to leverage the local information in image sequences to support global camera relocalization. In contrast to previous methods that regress global poses from single images, we exploit the spatial-temporal consistency in sequential…
Continual learning in large language models (LLMs) is prone to catastrophic forgetting, where adapting to new tasks significantly degrades performance on previously learned ones. Existing methods typically rely on low-rank,…