Related papers: UDAPose: Unsupervised Domain Adaptation for Low-Li…

Unsupervised domain adaptation (UDA) for semantic segmentation aims to adapt a segmentation model trained on the labeled source domain to the unlabeled target domain. Existing methods try to learn domain invariant features while suffering…

Articulation-centric 2D/3D pose supervision forms the core training objective in most existing 3D human pose estimation techniques. Except for synthetic source environments, acquiring such rich supervision for each real target domain at…

Conventional 2D human pose estimation methods typically require extensive labeled annotations, which are both labor-intensive and expensive. In contrast, semi-supervised 2D human pose estimation can alleviate the above problems by…

Despite its importance, unsupervised domain adaptation (UDA) on LiDAR semantic segmentation is a task that has not received much attention from the research community. Only recently, a completion-based 3D method has been proposed to tackle…

Unsupervised Domain Adaptation (UDA) aims to adapt models from labeled source domains to unlabeled target domains. When adapting to adverse scenes, existing UDA methods fail to perform well due to the lack of instructions, leading their…

As vision based perception methods are usually built on the normal light assumption, there will be a serious safety issue when deploying them into low light environments. Recently, deep learning based methods have been proposed to enhance…

Successful unsupervised domain adaptation is guaranteed only under strong assumptions such as covariate shift and overlap between input domains. The latter is often violated in high-dimensional applications like image classification which,…

Current exposure correction methods have three challenges, labor-intensive paired data annotation, limited generalizability, and performance degradation in low-level computer vision tasks. In this work, we introduce an innovative…

This paper presents the first study on Unsupervised Domain Adaptation (UDA) for multimodal 3D panoptic segmentation (mm-3DPS), aiming to improve generalization under domain shifts commonly encountered in real-world autonomous driving. A…

The advances in monocular 3D human pose estimation are dominated by supervised techniques that require large-scale 2D/3D pose annotations. Such methods often behave erratically in the absence of any provision to discard unfamiliar…

In the era of deep learning, human pose estimation from multiple cameras with unknown calibration has received little attention to date. We show how to train a neural model to perform this task with high precision and minimal latency…

Recently, there has been an arms race of pose forecasting methods aimed at solving the spatio-temporal task of predicting a sequence of future 3D poses of a person given a sequence of past observed ones. However, the lack of unified…

When enough annotated training data is available, supervised deep-learning algorithms excel at estimating human body pose and shape using a single camera. The effects of too little such data being available can be mitigated by using other…

Despite recent advances in facial recognition, there remains a fundamental issue concerning degradations in performance due to substantial perspective (pose) differences between enrollment and query (probe) imagery. Therefore, we propose a…

Rigid image alignment is a fundamental task in computer vision, while the traditional algorithms are either too sensitive to noise or time-consuming. Recent unsupervised image alignment methods developed based on spatial transformer…

In this paper, we propose a method for coarse camera pose computation which is robust to viewing conditions and does not require a detailed model of the scene. This method meets the growing need of easy deployment of robotics or augmented…

Human pose estimation has given rise to a broad spectrum of novel and compelling applications, including action recognition, sports analysis, as well as surveillance. However, accurate video pose estimation remains an open challenge. One…

The ability to perceive 3D human bodies from a single image has a multitude of applications ranging from entertainment and robotics to neuroscience and healthcare. A fundamental challenge in human mesh recovery is in collecting the ground…

Recent unsupervised domain adaptation (UDA) methods have shown great success in addressing classical domain shifts (e.g., synthetic-to-real), but they still suffer under complex shifts (e.g. geographical shift), where both the background…

We consider the task of visually estimating the relative pose of a drone racing gate in front of a nano-quadrotor, using a convolutional neural network pre-trained on simulated data to regress the gate's pose. Due to the sim-to-real gap,…