Related papers: Navigation domain representation for interactive m…
Sensing surroundings plays a crucial role in human spatial perception, as it extracts the spatial configuration of objects as well as the free space from the observations. To facilitate the robot perception with such a surrounding sensing…
Previous Vision-Language-Action models face critical limitations in navigation: scarce, diverse data from labor-intensive collection and static representations that fail to capture temporal dynamics and physical laws. We propose NavDreamer,…
Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potential to outperform the classical solutions developed for this…
Numerical simulations are commonly used to understand the parameter dependence of given spatio-temporal phenomena. Sampling a multi-dimensional parameter space and running the respective simulations leads to an ensemble of a large number of…
Some forms of novel visual media enable the viewer to explore a 3D scene from arbitrary viewpoints, by interpolating between a discrete set of original views. Compared to 2D imagery, these types of applications require much larger amounts…
Generating high-quality novel view renderings of 3D Gaussian Splatting (3DGS) in scenes featuring transient objects is challenging. We propose a novel hybrid representation, termed as HybridGS, using 2D Gaussians for transient objects per…
Cross-domain Recommendation systems leverage multi-domain user interactions to improve performance, especially in sparse data or new user scenarios. However, CDR faces challenges such as effectively capturing user preferences and avoiding…
Dichotomous Image Segmentation (DIS) has recently emerged towards high-precision object segmentation from high-resolution natural images. When designing an effective DIS model, the main challenge is how to balance the semantic dispersion of…
Multi-faceted data visualization typically involves several dedicated views. To create a comprehensive understanding of the data, users have to mentally integrate the information from the different views. This integration is hindered by…
Deep learning models tend to underperform in the presence of domain shifts. Domain transfer has recently emerged as a promising approach wherein images exhibiting a domain shift are transformed into other domains for augmentation or…
Multiple-view (MV) visualization provides a comprehensive and integrated perspective on complex data, establishing itself as an effective method for visual communication and exploratory data analysis. While existing studies have…
We propose an optical flow-guided approach for semi-supervised video object segmentation. Optical flow is usually exploited as additional guidance information in unsupervised video object segmentation. However, its relevance in…
Compactly representing the visual signals is of fundamental importance in various image/video-centered applications. Although numerous approaches were developed for improving the image and video coding performance by removing the…
Since their emergence, Convolutional Neural Networks (CNNs) have made significant strides in medical image analysis. However, the local nature of the convolution operator may pose a limitation for capturing global and long-range…
Novel view synthesis of static scenes has achieved remarkable advancements in producing photo-realistic results. However, key challenges remain for immersive rendering of dynamic scenes. One of the seminal image-based rendering method, the…
Multimodal datasets contain an enormous amount of relational information, which grows exponentially with the introduction of new modalities. Learning representations in such a scenario is inherently complex due to the presence of multiple…
Multihoming for a video Content Delivery Network (CDN) allows edge peering servers to deliver video chunks through different Internet Service Providers (ISPs), to achieve an improved quality of service (QoS) for video streaming users.…
Reconstructing general dynamic scenes is important for many computer vision and graphics applications. Recent works represent the dynamic scene with neural radiance fields for photorealistic view synthesis, while their surface geometry is…
In modern medical diagnostics, magnetic resonance imaging (MRI) is an important technique that provides detailed insights into anatomical structures. In this paper, we present a comprehensive methodology focusing on streamlining the…
Semantic Segmentation plays a pivotal role in many applications related to medical image and video analysis. However, designing a neural network architecture for medical image and surgical video segmentation is challenging due to the…