Related papers: Queryable 3D Scene Representation: A Multi-Modal F…

This thesis introduces "Embodied Spatial Intelligence" to address the challenge of creating robots that can perceive and act in the real world based on natural language instructions. To bridge the gap between Large Language Models (LLMs)…

Comprehensive scene understanding is a critical enabler of robot autonomy. Semantic segmentation is one of the key scene understanding tasks which is pivotal for several robotics applications including autonomous driving, domestic service…

Existing 3D scene generation methods often struggle to model the complex logical dependencies and physical constraints between objects, limiting their ability to adapt to dynamic and realistic environments. We propose CausalStruct, a novel…

Recent advancements in 3D perception systems have significantly improved their ability to perform visual recognition tasks such as segmentation. However, these systems still heavily rely on explicit human instruction to identify target…

Multimodal referring segmentation aims to segment target objects in visual scenes, such as images, videos, and 3D scenes, based on referring expressions in text or audio format. This task plays a crucial role in practical applications…

Semantic Scene Completion (SSC) aims to simultaneously predict the volumetric occupancy and semantic category of a 3D scene. It helps intelligent devices to understand and interact with the surrounding scenes. Due to the high-memory…

Multi-modal 3D scene understanding has gained considerable attention due to its wide applications in many areas, such as autonomous driving and human-computer interaction. Compared to conventional single-modal 3D understanding, introducing…

Safety-critical 3D scene understanding tasks necessitate not only accurate but also confident predictions from 3D perception models. This study introduces Calib3D, a pioneering effort to benchmark and scrutinize the reliability of 3D scene…

The rapid development of Large Multimodal Models (LMMs) has led to remarkable progress in 2D visual understanding; however, extending these capabilities to 3D scene understanding remains a significant challenge. Existing approaches…

Scene understanding is paramount in robotics, self-navigation, augmented reality, and many other fields. To fully accomplish this task, an autonomous agent has to infer the 3D structure of the sensed scene (to know where it looks at) and…

Reasoning about spatial relationships between objects is essential for many real-world robotic tasks, such as fetch-and-delivery, object rearrangement, and object search. The ability to detect and disambiguate different objects and identify…

Despite impressive advancements in Visual-Language Models (VLMs) for multi-modal tasks, their reliance on RGB inputs limits precise spatial understanding. Existing methods for integrating spatial cues, such as point clouds or depth, either…

Gaussian Splatting has rapidly emerged as a transformative technique for real-time 3D scene representation, offering a highly efficient and expressive alternative to Neural Radiance Fields (NeRF). Its ability to render complex scenes with…

In this paper, we rethink the problem of scene reconstruction from an embodied agent's perspective: While the classic view focuses on the reconstruction accuracy, our new perspective emphasizes the underlying functions and constraints such…

Despite the impressive progress on understanding and generating images shown by the recent unified architectures, the integration of 3D tasks remains challenging and largely unexplored. In this paper, we introduce UniUGG, the first unified…

Recent advances in Large Language Models (LLMs) have helped facilitate exciting progress for robotic planning in real, open-world environments. 3D scene graphs (3DSGs) offer a promising environment representation for grounding such…

While Multimodal Large Language Models (MLLMs) have achieved remarkable success in 2D visual understanding, their ability to reason about 3D space remains limited. To address this gap, we introduce geometrically referenced 3D scene…

Representations are crucial for a robot to learn effective navigation policies. Recent work has shown that mid-level perceptual abstractions, such as depth estimates or 2D semantic segmentation, lead to more effective policies when provided…

Utilizing functional elements in an industrial environment, such as displays and interactive valves, provide effective possibilities for robot training. When preparing simulations for robots or applications that involve high-level scene…

Open-vocabulary 3D Scene Graph (3DSG) can enhance various downstream tasks in robotics by leveraging structured semantic representations, yet current 3DSG construction methods suffer from semantic inconsistencies caused by noisy cross-image…