Related papers: SceneGraphGrounder: Zero-Shot 3D Visual Grounding …
In data-driven storytelling contexts such as data journalism and data videos, data visualizations are often presented alongside real-world imagery to support narrative context. However, these visualizations and contextual images typically…
Stimulated by the sophisticated reasoning capabilities of recent Large Language Models (LLMs), a variety of strategies for bridging video modality have been devised. A prominent strategy involves Video Language Models (VideoLMs), which…
Many public buildings provide floorplans with a "you are here" indicator to help visitors orient themselves. Floorplan localization seeks to computationally replicate this capability by determining where visual observations were captured…
While Vision-Language Models (VLMs) show significant promise for end-to-end autonomous driving by leveraging the common sense embedded in language models, their reliance on 2D image cues for complex scene understanding and decision-making…
Vision-language models have recently emerged as promising planners for autonomous driving, where success hinges on topology-aware reasoning over spatial structure and dynamic interactions from multimodal input. However, existing models are…
Semantic 3D scene understanding is a problem of critical importance in robotics. While significant advances have been made in simultaneous localization and mapping algorithms, robots are still far from having the common sense knowledge…
A robust visual localization and mapping system is essential for warehouse robot navigation, as cameras offer a more cost-effective alternative to LiDAR sensors. However, existing forward-facing camera systems often encounter challenges in…
Language-guided embodied navigation requires an agent to interpret object-referential instructions, search across multiple rooms, localize the referenced target, and execute reliable motion toward it. Existing systems remain limited in real…
Object navigation (ObjectNav) requires an agent to navigate through unseen environments to find queried objects. Many previous methods attempted to solve this task by relying on supervised or reinforcement learning, where they are trained…
The bundle of geometry and appearance in computer vision has proven to be a promising solution for robots across a wide variety of applications. Stereo cameras and RGB-D sensors are widely used to realise fast 3D reconstruction and…
D scene graphs are an emerging 3D scene representation, that models both the objects present in the scene as well as their relationships. However, learning 3D scene graphs is a challenging task because it requires not only object labels but…
Grounded video description (GVD) encourages captioning models to attend to appropriate video regions (e.g., objects) dynamically and generate a description. Such a setting can help explain the decisions of captioning models and prevents the…
Cross-View Geo-Localization (CVGL) in remote sensing aims to locate a drone-view query by matching it to geo-tagged satellite images. Although supervised methods have achieved strong results on closeset benchmarks, they often fail to…
Visual question answering is concerned with answering free-form questions about an image. Since it requires a deep linguistic understanding of the question and the ability to associate it with various objects that are present in the image,…
We present 3DScenePrompt, a framework that generates the next video chunk from arbitrary-length input while enabling precise camera control and preserving scene consistency. Unlike methods conditioned on a single image or a short clip, we…
Reconstructing accurate 3D models of large-scale real-world scenes from unstructured, in-the-wild imagery remains a core challenge in computer vision, especially when the input views have little or no overlap. In such cases, existing…
Recent advances have demonstrated that Language Vision Models (LVMs) surpass the existing State-of-the-Art (SOTA) in two-dimensional (2D) computer vision tasks, motivating attempts to apply LVMs to three-dimensional (3D) data. While LVMs…
Compared with the visual grounding on 2D images, the natural-language-guided 3D object localization on point clouds is more challenging. In this paper, we propose a new model, named InstanceRefer, to achieve a superior 3D visual grounding…
Referential grounding in outdoor driving scenes is challenging due to large scene variability, many visually similar objects, and dynamic elements that complicate resolving natural-language references (e.g., "the black car on the right").…
Robotic grasping is a fundamental capability for enabling autonomous manipulation, with usually infinite solutions. State-of-the-art approaches for grasping rely on learning from large-scale datasets comprising expert annotations of…