Related papers: Uncertainty-Instructed Structure Injection for Gen…
Inverse problems and, in particular, inferring unknown or latent parameters from data are ubiquitous in engineering simulations. A predominant viewpoint in identifying unknown parameters is Bayesian inference where both prior information…
In this paper, we present an active exploration framework for high-fidelity 3D reconstruction that incrementally builds a multi-level uncertainty space and selects next-best-views through an uncertainty-driven motion planner. We introduce a…
Classifying incomplete multi-view data is inevitable since arbitrary view missing widely exists in real-world applications. Although great progress has been achieved, existing incomplete multi-view methods are still difficult to obtain a…
Inspired by the development of deep learning in computer vision and object detection, the proposed algorithm considers an encoder-decoder architecture with hierarchical feature learning and dilated convolution, named U-Hierarchical Dilated…
To predict high-resolution (HR) omnidirectional depth map, existing methods typically leverage HR omnidirectional image (ODI) as the input via fully-supervised learning. However, in practice, taking HR ODI as input is undesired due to…
The uncertainty quantification of sensor measurements coupled with deep learning networks is crucial for many robotics systems, especially for safety-critical applications such as self-driving cars. This paper develops an uncertainty…
3D object detection is an essential task for computer vision applications in autonomous vehicles and robotics. However, models often struggle to quantify detection reliability, leading to poor performance on unfamiliar scenes. We introduce…
High-definition (HD) map serves as the essential infrastructure of autonomous driving. In this work, we build up a systematic vectorized map annotation framework (termed VMA) for efficiently generating HD map of large-scale driving scene.…
High-definition (HD) semantic maps are crucial in enabling autonomous vehicles to navigate urban environments. The traditional method of creating offline HD maps involves labor-intensive manual annotation processes, which are not only…
Autonomous driving has been among the most popular and challenging topics in the past few years. On the road to achieving full autonomy, researchers have utilized various sensors, such as LiDAR, camera, Inertial Measurement Unit (IMU), and…
To autonomously navigate in real-world environments, special in search and rescue operations, Unmanned Aerial Vehicles (UAVs) necessitate comprehensive maps to ensure safety. However, the prevalent metric map often lacks semantic…
Computational image reconstruction algorithms generally produce a single image without any measure of uncertainty or confidence. Regularized Maximum Likelihood (RML) and feed-forward deep learning approaches for inverse problems typically…
Most mobile robots for indoor use rely on 2D laser scanners for localization, mapping and navigation. These sensors, however, cannot detect transparent surfaces or measure the full occupancy of complex objects such as tables. Deep Neural…
GUI grounding, which translates natural language instructions into precise pixel coordinates, is essential for developing practical GUI agents. However, we observe that existing grounding models exhibit significant coordinate prediction…
Ultra-high-definition (UHD) video denoising requires simultaneously suppressing complex spatio-temporal degradations, preserving fine textures and chromatic stability, and maintaining efficient full-resolution 4K deployment. In this paper,…
Pre-trained point cloud analysis models have shown promising advancements in various downstream tasks, yet their effectiveness is typically suffering from low-quality point cloud (i.e., noise and incompleteness), which is a common issue in…
Traffic accidents present substantial challenges to human safety and socio-economic development in urban areas. Developing a reliable and responsible traffic accident prediction model is crucial to addressing growing public safety concerns…
Uncertain knowledge graph embedding (UnKGE) methods learn vector representations that capture both structural and uncertainty information to predict scores of unseen triples. However, existing methods produce only point estimates, without…
Comprehensive visual, geometric, and semantic understanding of a 3D scene is crucial for successful execution of robotic tasks, especially in unstructured and complex environments. Additionally, to make robust decisions, it is necessary for…
Recent advances in deep learning have led to its widespread adoption across diverse domains, including medical imaging. This progress is driven by increasingly sophisticated model architectures, such as ResNets, Vision Transformers, and…