Related papers: Ges3ViG: Incorporating Pointing Gestures into Lang…
One of the main goals of robotics and intelligent agent research is to enable natural communication with humans in physically situated settings. While recent work has focused on verbal modes such as language and speech, non-verbal…
Embodied agents are expected to assist humans by actively exploring unknown environments and reasoning about spatial contexts. When deployed in real life, agents often face sequential tasks where each new task follows the completion of the…
A metric-accurate semantic 3D representation is essential for many robotic tasks. This work proposes a simple, yet powerful, way to integrate the 2D embeddings of a Vision-Language Model in a metric-accurate 3D representation at real-time.…
We introduce the task of 3D visual grounding in large-scale dynamic scenes based on natural linguistic descriptions and online captured multi-modal visual data, including 2D images and 3D LiDAR point clouds. We present a novel method,…
Vision-Language-Action (VLA) models have emerged as a promising approach for enabling robots to follow language instructions and predict corresponding actions. However, current VLA models mainly rely on 2D visual inputs, neglecting the rich…
Referring expression comprehension (REC) aims at achieving object localization based on natural language descriptions. However, existing REC approaches are constrained by object category descriptions and single-attribute intention…
Robust 3D geometry estimation from videos is critical for applications such as autonomous navigation, SLAM, and 3D scene reconstruction. Recent methods like DUSt3R demonstrate that regressing dense pointmaps from image pairs enables…
Prior studies on 3D scene understanding have primarily developed specialized models for specific tasks or required task-specific fine-tuning. In this study, we propose Grounded 3D-LLM, which explores the potential of 3D large multi-modal…
Multimodal Large Language Models (MLLMs) have made impressive progress in connecting vision and language, but they still struggle with spatial understanding and viewpoint-aware reasoning. Recent efforts aim to augment the input…
Joint video-language learning has received increasing attention in recent years. However, existing works mainly focus on single or multiple trimmed video clips (events), which makes human-annotated event boundaries necessary during…
Embodied intelligence fundamentally requires a capability to determine where to act in 3D space. We formalize this requirement as embodied localization -- the problem of predicting executable 3D points conditioned on visual observations and…
3D visual grounding (VG) aims to locate objects or regions within 3D scenes guided by natural language descriptions. While indoor 3D VG has advanced, outdoor 3D VG remains underexplored due to two challenges: (1) large-scale outdoor LiDAR…
Passive visual systems typically fail to recognize objects in the amodal setting where they are heavily occluded. In contrast, humans and other embodied agents have the ability to move in the environment, and actively control the viewing…
Recent advances in visual generative models have highlighted the promise of learning generative world models. However, most existing approaches frame world modeling as novel-view synthesis or future-frame prediction, emphasizing visual…
A robot's ability to anticipate the 3D action target location of a hand's movement from egocentric videos can greatly improve safety and efficiency in human-robot interaction (HRI). While previous research predominantly focused on semantic…
Generalized visual grounding tasks, including Generalized Referring Expression Comprehension (GREC) and Segmentation (GRES), extend the classical visual grounding paradigm by accommodating multi-target and non-target scenarios.…
Embodied perception is essential for intelligent vehicles and robots in interactive environmental understanding. However, these advancements primarily focus on vision, with limited attention given to using 3D modeling sensors, restricting a…
Accurate volume estimation of objects from visual data is a long-standing challenge in computer vision with significant applications in robotics, logistics, and smart health. Existing methods often rely on complex 3D reconstruction…
3D visual grounding (3DVG) is a critical task in scene understanding that aims to identify objects in 3D scenes based on text descriptions. However, existing methods rely on separately pre-trained vision and text encoders, resulting in a…
In embodied intelligence systems, a key component is 3D perception algorithm, which enables agents to understand their surrounding environments. Previous algorithms primarily rely on point cloud, which, despite offering precise geometric…