Related papers: DASP: Self-supervised Nighttime Monocular Depth Es…

Solving depth estimation with monocular cameras enables the possibility of widespread use of cameras as low-cost depth estimation sensors in applications such as autonomous driving and robotics. However, learning such a scalable depth…

Convolutional networks have marked their place over the last few years as the best performing model for various visual tasks. They are, however, most suited for supervised learning from large amounts of labeled data. Previous attempts have…

Depth estimation from monocular images is an important task in localization and 3D reconstruction pipelines for bronchoscopic navigation. Various supervised and self-supervised deep learning-based approaches have proven themselves on this…

Spatial-temporal graph learning has emerged as a promising solution for modeling structured spatial-temporal data and learning region representations for various urban sensing tasks such as crime forecasting and traffic flow prediction.…

The pretraining-finetuning paradigm is a crucial strategy in metallic surface defect detection for mitigating the challenges posed by data scarcity. However, its implementation presents a critical dilemma. Pretraining on natural image…

This paper studies unsupervised monocular depth prediction problem. Most of existing unsupervised depth prediction algorithms are developed for outdoor scenarios, while the depth prediction work in the indoor environment is still very…

The goal of fine-grained action recognition is to successfully discriminate between action categories with subtle differences. To tackle this, we derive inspiration from the human visual system which contains specialized regions in the…

Pre-training has become a standard paradigm in many computer vision tasks. However, most of the methods are generally designed on the RGB image domain. Due to the discrepancy between the two-dimensional image plane and the three-dimensional…

This paper presents a visual SLAM system that uses both points and lines for robust camera localization, and simultaneously performs a piece-wise planar reconstruction (PPR) of the environment to provide a structural map in real-time. One…

Convolutional networks have marked their place over the last few years as the best performing model for various visual tasks. They are, however, most suited for supervised learning from large amounts of labeled data. Previous attempts have…

This letter introduces a novel framework for dense Visual Simultaneous Localization and Mapping (VSLAM) based on Gaussian Splatting. Recently, SLAM based on Gaussian Splatting has shown promising results. However, in monocular scenarios,…

Contrastive learning has shown promising potential in self-supervised spatio-temporal representation learning. Most works naively sample different clips to construct positive and negative pairs. However, we observe that this formulation…

Mapping and 3D detection are two major issues in vision-based robotics, and self-driving. While previous works only focus on each task separately, we present an innovative and efficient multi-task deep learning framework (SM3D) for…

Unsupervised monocular depth estimation techniques have demonstrated encouraging results but typically assume that the scene is static. These techniques suffer when trained on dynamical scenes, where apparent object motion can equally be…

We consider the problem of semi-supervised 3D action recognition which has been rarely explored before. Its major challenge lies in how to effectively learn motion representations from unlabeled data. Self-supervised learning (SSL) has been…

Monocular depth estimation using Convolutional Neural Networks (CNNs) has shown impressive performance in outdoor driving scenes. However, self-supervised learning of indoor depth from monocular sequences is quite challenging for…

Medical endoscopy remains a challenging application for simultaneous localization and mapping (SLAM) due to the sparsity of image features and size constraints that prevent direct depth-sensing. We present a SLAM approach that incorporates…

Most existing CNN-based super-resolution (SR) methods are developed based on an assumption that the degradation is fixed and known (e.g., bicubic downsampling). However, these methods suffer a severe performance drop when the real…

Motion Planning, as a fundamental technology of automatic navigation for the autonomous vehicle, is still an open challenging issue in the real-life traffic situation and is mostly applied by the model-based approaches. However, due to the…

Unsupervised methods have showed promising results on monocular depth estimation. However, the training data must be captured in scenes without moving objects. To push the envelope of accuracy, recent methods tend to increase their model…