12 accepted papers
This paper tackles the challenge of recovering 4D dynamic scenes from videos captured by as few as four portable cameras. Learning to model scene dynamics for temporally consistent novel-view rendering is a foundational task in computer graphics, where previous works often require dense multi-view c
Imitation learning is a critical approach for robots to acquire skills by mimicking human behavior. However, traditional imitation learning frameworks often exhibit poor action prediction accuracy and low robustness when handling complex tasks. To tackle these limitations, we propose the PIDiff poli
Reconstructing a faithful geometric surface from sparse images remains a fundamental challenge in 3D computer vision. While recent methods have achieved remarkable progress, they still struggle to recover reliable geometry due to the lack of multi-view geometric cues, particularly in non-overlapping
Catching flying objects with a cushioning process is a skill commonly performed by humans, yet it remains a significant challenge for robots. In this paper, we present a framework that combines optimization and learning to achieve compliant catching on mobile manipulators (CCMM). First, we propose a
Monocular depth priors have been widely adopted by neural rendering in multi-view based tasks such as 3D reconstruction and novel view synthesis. However, due to the inconsistent prediction on each view, how to more effectively leverage monocular cues in a multi-view context remains a challenge. Cur…
Surface reconstruction from sparse views aims to reconstruct a 3D shape or scene from few RGB images. The latest methods are either generalization-based or overfitting-based. However, the generalization-based methods do not generalize well on views that were unseen during training, while the reconst…
Building a universal trajectory foundation model is a promising solution to address the limitations of existing trajectory modeling approaches, such as task specificity, regional dependency, and data sensitivity. Despite its potential, data preparation, pre-training strategy development, and archite…
Novel view synthesis from sparse inputs is a vital yet challenging task in 3D computer vision. Previous methods explore 3D Gaussian Splatting with neural priors (e.g. depth priors) as an additional supervision, demonstrating promising quality and efficiency compared to the NeRF based methods. Howeve…
Large-scale UAV switching formation tracking control has been widely applied in many fields such as search and rescue, cooperative transportation, and UAV light shows. In order to optimize the control performance and reduce the computational burden of the system, this study proposes an event-trigger…
Augmented reality (AR) technology has been in-troduced into the robotics field to narrow the visual gap between indoor and outdoor environments. However, without signals from satellite navigation systems, flight experiments in these indoor AR scenarios need other accurate localization approaches. Th…
For traditional manipulators, there is a large number of electrical cables between the motion controller and the joint servo controllers. It is very inconvenient for maintenance, update, and safe operation. In this paper, we develop a lightweight redundant manipulator with high stable wireless commu…
Cross-modal retrieval, which aims to solve the problem that the query and the retrieved results are from different modality, becomes more and more essential with the development of the Internet. In this paper, we mainly focus on the exploration of high-level semantic representation of image and text…