Related papers: RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot G…

3D Gaussian splatting (3DGS) has demonstrated impressive performance in synthesizing high-fidelity novel views. Nonetheless, its effectiveness critically depends on the quality of the initialized point cloud. Specifically, achieving uniform…

Driven by recent advancements in foundation models, semantic scene graphs have emerged as a promising paradigm for high-level 3D environmental abstraction in robot navigation. However, existing frameworks struggle to successfully handle…

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…

Integrating open-vocabulary semantic information into dynamic 3D scene representations is essential for long-term embodied scene understanding. However, existing methods often suffer from fragile instance association due to incomplete…

Retrieval-Augmented Generation (RAG) has become a core paradigm for enhancing factual grounding and multi-hop reasoning in Large Language Models (LLMs). Traditional text-based RAG often retrieves logically irrelevant pseudo-evidence, while…

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…

3D Gaussian Splatting (3DGS) has emerged as a promising approach for 3D scene representation, offering a reduction in computational overhead compared to Neural Radiance Fields (NeRF). However, 3DGS is susceptible to high-frequency artifacts…

Mapping and scene representation are fundamental to reliable planning and navigation in mobile robots. While purely geometric maps using voxel grids allow for general navigation, obtaining up-to-date spatial and semantically rich…

Building upon the standard graph-based Retrieval-Augmented Generation (RAG), the introduction of heterogeneous graphs and hypergraphs aims to enrich retrieval and generation by leveraging the relationships between multiple entities through…

Current general-purpose large language models (LLMs) commonly exhibit knowledge hallucination and insufficient domain-specific adaptability in domain-specific tasks, limiting their effectiveness in specialized question answering scenarios.…

Retrieval-augmented generation (RAG) is a powerful technique that enhances downstream task execution by retrieving additional information, such as knowledge, skills, and tools from external sources. Graph, by its intrinsic "nodes connected…

Scene graphs are a compact and explicit representation successfully used in a variety of 2D scene understanding tasks. This work proposes a method to incrementally build up semantic scene graphs from a 3D environment given a sequence of…

Open-vocabulary 3D scene understanding presents a significant challenge in computer vision, with wide-ranging applications in embodied agents and augmented reality systems. Existing methods adopt neurel rendering methods as 3D…

Latent scene representation plays a significant role in training reinforcement learning (RL) agents. To obtain good latent vectors describing the scenes, recent works incorporate the 3D-aware latent-conditioned NeRF pipeline into scene…

3D Gaussian Splatting (3DGS) has achieved impressive rendering performance in novel view synthesis. However, its efficacy diminishes considerably in sparse image sequences, where inherent data sparsity amplifies geometric uncertainty during…

Novel view synthesis from raw images provides superior high dynamic range (HDR) information compared to reconstructions from low dynamic range RGB images. However, the inherent noise in unprocessed raw images compromises the accuracy of 3D…

The primary focus of most recent works on open-vocabulary neural fields is extracting precise semantic features from the VLMs and then consolidating them efficiently into a multi-view consistent 3D neural fields representation. However,…

3D Gaussian Splatting (3DGS) has shown remarkable potential for static scene reconstruction, and recent advancements have extended its application to dynamic scenes. However, the quality of reconstructions depends heavily on high-quality…

3D Gaussian Splatting (3DGS) has emerged as a transformative method in the field of real-time novel synthesis. Based on 3DGS, recent advancements cope with large-scale scenes via spatial-based partition strategy to reduce video memory and…

3D Gaussian Splatting is renowned for its high-fidelity reconstructions and real-time novel view synthesis, yet its lack of semantic understanding limits object-level perception. In this work, we propose ObjectGS, an object-aware framework…