相关论文: FreeQ-Graph: Free-form Querying with Semantic Cons…

Open-world 3D scene understanding is a critical challenge that involves recognizing and distinguishing diverse objects and categories from 3D data, such as point clouds, without relying on manual annotations. Traditional methods struggle…

Recent advances in metric, semantic, and topological mapping have equipped autonomous robots with semantic concept grounding capabilities to interpret natural language tasks. This work aims to leverage these new capabilities with an…

Learning 3D scene geometry and semantics from images is a core challenge in computer vision and a key capability for autonomous driving. Since large-scale 3D annotation is prohibitively expensive, recent work explores self-supervised…

Scene understanding has been of high interest in computer vision. It encompasses not only identifying objects in a scene, but also their relationships within the given context. With this goal, a recent line of works tackles 3D semantic…

Effective scene representation is critical for the visual grounding ability of representations, yet existing methods for 3D Visual Grounding are often constrained. They either only focus on geometric and visual cues, or, like traditional 3D…

We present LinkQ, a system that leverages a large language model (LLM) to facilitate knowledge graph (KG) query construction through natural language question-answering. Traditional approaches often require detailed knowledge of a graph…

Recent advances in 3D scene-language understanding have leveraged Large Language Models (LLMs) for 3D reasoning by transferring their general reasoning ability to 3D multi-modal contexts. However, existing methods typically adopt standard…

The remarkable potential of multi-modal large language models (MLLMs) in comprehending both vision and language information has been widely acknowledged. However, the scarcity of 3D scenes-language pairs in comparison to their 2D…

Locating objects described in natural language presents a significant challenge for autonomous agents. Existing CLIP-based open-vocabulary methods successfully perform 3D object grounding with simple (bare) queries, but cannot cope with…

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…

Compositional 3D scene synthesis has diverse applications across a spectrum of industries such as robotics, films, and video games, as it closely mirrors the complexity of real-world multi-object environments. Conventional works typically…

3D semantic scene graphs are a powerful holistic representation as they describe the individual objects and depict the relation between them. They are compact high-level graphs that enable many tasks requiring scene reasoning. In real-world…

Graph-based representations such as Scene Graphs enable localization in structured indoor environments by matching a locally observed graph, constructed from sensor data, to a prior map. This process is particularly challenging in…

Most deep learning approaches to comprehensive semantic modeling of 3D indoor spaces require costly dense annotations in the 3D domain. In this work, we explore a central 3D scene modeling task, namely, semantic scene reconstruction without…

Large Language Models (LLMs) have shown strong capabilities in solving problems across domains, including graph-related tasks traditionally addressed by symbolic or algorithmic methods. In this work, we present a framework for structured…

We introduce ScanComplete, a novel data-driven approach for taking an incomplete 3D scan of a scene as input and predicting a complete 3D model along with per-voxel semantic labels. The key contribution of our method is its ability to…

Reasoning segmentation aims to segment target objects in complex scenes based on human intent and spatial reasoning. While recent multimodal large language models (MLLMs) have demonstrated impressive 2D image reasoning segmentation,…

Although Multimodal Large Language Models have achieved remarkable progress, they still struggle with complex 3D spatial reasoning due to the reliance on 2D visual priors. Existing approaches typically mitigate this limitation either…

Vision-language models (VLMs) demonstrate strong image-level scene understanding but often lack persistent memory, explicit spatial representations, and computational efficiency when reasoning over long video sequences. We present VL-KnG, a…

3D point cloud segmentation aims to assign semantic labels to individual points in a scene for fine-grained spatial understanding. Existing methods typically adopt data augmentation to alleviate the burden of large-scale annotation.…