Related papers: ChangingGrounding: 3D Visual Grounding in Changing…
Deep neural network models have achieved remarkable progress in 3D scene understanding while trained in the closed-set setting and with full labels. However, the major bottleneck is that these models do not have the capacity to recognize…
Visual target navigation is a critical capability for autonomous robots operating in unknown environments, particularly in human-robot interaction scenarios. While classical and learning-based methods have shown promise, most existing…
As robots begin to cohabit with humans in semi-structured environments, the need arises to understand instructions involving rich variability---for instance, learning to ground symbols in the physical world. Realistically, this task must…
Nowadays robots play an increasingly important role in our daily life. In human-centered environments, robots often encounter piles of objects, packed items, or isolated objects. Therefore, a robot must be able to grasp and manipulate…
Rather than having each newly deployed robot create its own map of its surroundings, the growing availability of SLAM-enabled devices provides the option of simply localizing in a map of another robot or device. In cases such as multi-robot…
We introduce the novel task of Language-Guided Object Placement in Real 3D Scenes. Our model is given a 3D scene's point cloud, a 3D asset, and a textual prompt broadly describing where the 3D asset should be placed. The task here is to…
Remote sensing (RS) visual grounding aims to use natural language expression to locate specific objects (in the form of the bounding box or segmentation mask) in RS images, enhancing human interaction with intelligent RS interpretation…
The field of collaborative robotics and human-robot interaction often focuses on the prediction of human behaviour, while assuming the information about the robot setup and configuration being known. This is often the case with fixed…
Reconstructing dynamic 4D scenes is challenging, as it requires robust disentanglement of dynamic objects from the static background. While 3D foundation models like VGGT provide accurate 3D geometry, their performance drops markedly when…
Camera relocalization, a cornerstone capability of modern computer vision, accurately determines a camera's position and orientation (6-DoF) from images and is essential for applications in augmented reality (AR), mixed reality (MR),…
The grand vision of enabling persistent, large-scale 3D visual geometry understanding is shackled by the irreconcilable demands of scalability and long-term stability. While offline models like VGGT achieve inspiring geometry capability,…
Maintaining an up-to-date map that accurately reflects recent changes in the environment is crucial, especially for robots that repeatedly traverse the same space. Failing to promptly update the changed regions can degrade map quality,…
Visual grounding is a ubiquitous building block in many vision-language tasks and yet remains challenging due to large variations in visual and linguistic features of grounding entities, strong context effect and the resulting semantic…
To autonomously navigate and plan interactions in real-world environments, robots require the ability to robustly perceive and map complex, unstructured surrounding scenes. Besides building an internal representation of the observed scene…
Visual localization has traditionally been formulated as a pair-wise pose regression problem. Existing approaches mainly estimate relative poses between two images and employ a late-fusion strategy to obtain absolute pose estimates.…
High-level autonomous operations depend on a robot's ability to construct a sufficiently expressive model of its environment. Traditional three-dimensional (3D) scene representations, such as point clouds and occupancy grids, provide…
Robotic scene understanding increasingly relies on Vision-Language Models (VLMs) to generate natural language descriptions of the environment. In this work, we systematically evaluate single-view object captioning for tabletop scenes…
Recent approaches in text-to-image customization have primarily focused on preserving the identity of the input subject, but often fail to control the spatial location and size of objects. We introduce GroundingBooth, which achieves…
Robots are finding wider adoption in human environments, increasing the need for natural human-robot interaction. However, understanding a natural language command requires the robot to infer the intended task and how to decompose it into…
This paper presents a framework for jointly grounding objects that follow certain semantic relationship constraints given in a scene graph. A typical natural scene contains several objects, often exhibiting visual relationships of varied…