Related papers: Project Elements: A computational entity-component…

Assisted by neural networks, reinforcement learning agents have been able to solve increasingly complex tasks over the last years. The simulation environment in which the agents interact is an essential component in any reinforcement…

Collective Perception has attracted significant attention in recent years due to its advantage for mitigating occlusion and expanding the field-of-view, thereby enhancing reliability, efficiency, and, most crucially, decision-making safety.…

Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices. While hand-designed features on point clouds have long…

We propose UniSeg3D, a unified 3D scene understanding framework that achieves panoptic, semantic, instance, interactive, referring, and open-vocabulary segmentation tasks within a single model. Most previous 3D segmentation approaches are…

Generalizable Gaussian Splatting aims to synthesize novel views for unseen scenes without per-scene optimization. In particular, recent advancements utilize feed-forward networks to predict per-pixel Gaussian parameters, enabling…

This paper investigates the integration of graph neural networks (GNNs) with Qualitative Explainable Graphs (QXGs) for scene understanding in automated driving. Scene understanding is the basis for any further reactive or proactive…

Sometimes the meaning conveyed by images goes beyond the list of objects they contain; instead, images may express a powerful message to affect the viewers' minds. Inferring this message requires reasoning about the relationships between…

3D semantic segmentation is a fundamental building block for several scene understanding applications such as autonomous driving, robotics and AR/VR. Several state-of-the-art semantic segmentation models suffer from the part…

Computer science education has evolved extensively; however, systemic barriers still prevent students with visual impairments from fully participating. While existing research has developed specialized programming tools and assistive…

Segmentation-based tracking has been actively studied in computer vision and multimedia. Superpixel based object segmentation and tracking methods are usually developed for this task. However, they independently perform feature…

The boundary element method (BEM) provides an efficient numerical framework for solving multiple scattering problems in unbounded homogeneous domains, since it reduces the discretization to the domain boundaries, thereby condensing the…

This position paper argues for the use of \emph{structured generative models} (SGMs) for the understanding of static scenes. This requires the reconstruction of a 3D scene from an input image (or a set of multi-view images), whereby the…

The finite element method offers attractive methods for the numerical solution of coupled field problems arising in sensors and actuator simulations of various physical domains, like electrodynamics, mechanics, and thermodynamics. With this…

Over the years, datasets and benchmarks have had an outsized influence on the design of novel algorithms. In this paper, we introduce ChairSegments, a novel and compact semi-synthetic dataset for object segmentation. We also show empirical…

Transparent object perception remains a major challenge in computer vision research, as transparency confounds both depth estimation and semantic segmentation. Recent work has explored multi-task learning frameworks to improve robustness,…

In real-world scenarios, although data entities may possess inherent relationships, the specific graph illustrating their connections might not be directly accessible. Latent graph inference addresses this issue by enabling Graph Neural…

Graph Neural Networks (GNNs) have demonstrated significant success in learning from graph-structured data but often struggle on heterophilous graphs, where connected nodes differ in features or class labels. This limitation arises from…

Recent advancements in 3D Gaussian Splatting(3DGS) have significantly improved semantic scene understanding, enabling natural language queries to localize objects within a scene. However, existing methods primarily focus on embedding…

E-learning can be loosely defined as a wide set of applications and processes, which uses available electronic media (and tools) to deliver vocational education and training. With its increasing recognition as an ubiquitous mode of…

Conversational Speech Synthesis (CSS) aims to accurately express an utterance with the appropriate prosody and emotional inflection within a conversational setting. While recognising the significance of CSS task, the prior studies have not…