相关论文: Test-Time Adaptation for Keypoint-Based Spacecraft…

While pose estimation is an important computer vision task, it requires expensive annotation and suffers from domain shift. In this paper, we investigate the problem of domain adaptive 2D pose estimation that transfers knowledge learned on…

In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions. We turn a single unlabeled test sample into a self-supervised…

In contrast to close-set scenarios that restore images from a predefined set of degradations, open-set image restoration aims to handle the unknown degradations that were unforeseen during the pretraining phase, which is less-touched as far…

Keypoint detection is an essential building block for many robotic applications like motion capture and pose estimation. Historically, keypoints are detected using uniquely engineered markers such as checkerboards or fiducials. More…

Autonomous vision-based spaceborne navigation is an enabling technology for future on-orbit servicing and space logistics missions. While computer vision in general has benefited from Machine Learning (ML), training and validating…

The detection and tracking of celestial surface terrain features are crucial for autonomous spaceflight applications, including Terrain Relative Navigation (TRN), Entry, Descent, and Landing (EDL), hazard analysis, and scientific data…

6D Object pose estimation is a fundamental component in robotics enabling efficient interaction with the environment. It is particularly challenging in bin-picking applications, where objects may be textureless and in difficult poses, and…

Modern self-supervised learning algorithms typically enforce persistency of instance representations across views. While being very effective on learning holistic image and video representations, such an objective becomes sub-optimal for…

Adaptation of pretrained vision-language models such as CLIP to various downstream tasks have raised great interest in recent researches. Previous works have proposed a variety of test-time adaptation (TTA) methods to achieve strong…

Tracking the 6D pose of objects in video sequences is important for robot manipulation. This work presents se(3)-TrackNet, a data-driven optimization approach for long term, 6D pose tracking. It aims to identify the optimal relative pose…

Estimating the pose of an uncooperative spacecraft is an important computer vision problem for enabling the deployment of automatic vision-based systems in orbit, with applications ranging from on-orbit servicing to space debris removal.…

LiDAR place recognition approaches based on deep learning suffer from significant performance degradation when there is a shift between the distribution of training and test datasets, often requiring re-training the networks to achieve peak…

An unresolved problem in Deep Learning is the ability of neural networks to cope with domain shifts during test-time, imposed by commonly fixing network parameters after training. Our proposed method Meta Test-Time Training (MT3), however,…

Reconstructing 3D from a single view image is a long-standing challenge. One of the popular approaches to tackle this problem is learning-based methods, but dealing with the test cases unfamiliar with training data (Out-of-distribution;…

Two-view pose estimation is essential for map-free visual relocalization and object pose tracking tasks. However, traditional matching methods suffer from time-consuming robust estimators, while deep learning-based pose regressors only…

This work proposes a process for efficiently training a point-wise object detector that enables localizing objects and computing their 6D poses in cluttered and occluded scenes. Accurate pose estimation is typically a requirement for robust…

Mutual localization stands as a foundational component within various domains of multi-robot systems. Nevertheless, in relative pose estimation, time synchronization is usually underappreciated and rarely addressed, although it…

Although action recognition systems can achieve top performance when evaluated on in-distribution test points, they are vulnerable to unanticipated distribution shifts in test data. However, test-time adaptation of video action recognition…

Foundation models have recently gained attention within the field of machine learning thanks to its efficiency in broad data processing. While researchers had attempted to extend this success to time series models, the main challenge is…

3-D pose estimation of instruments is a crucial step towards automatic scene understanding in robotic minimally invasive surgery. Although robotic systems can potentially directly provide joint values, this information is not commonly…