Related papers: LatentAM: Real-Time, Large-Scale Latent Gaussian A…
3D Gaussian Splatting (3DGS) based Simultaneous Localization and Mapping (SLAM) systems can largely benefit from 3DGS's state-of-the-art rendering efficiency and accuracy, but have not yet been adopted in resource-constrained edge devices…
Achieving unified 3D perception and reasoning across tasks such as segmentation, retrieval, and relation understanding remains challenging, as existing methods are either object-centric or rely on costly training for inter-object reasoning.…
3D Gaussian Splatting offers expressive scene reconstruction, modeling a broad range of visual, geometric, and semantic information. However, efficient real-time map reconstruction with data streamed from multiple robots and devices remains…
Recently, the 3D Gaussian Splatting (3D-GS) method has achieved great success in novel view synthesis, providing real-time rendering while ensuring high-quality rendering results. However, this method faces challenges in modeling specular…
3D Gaussian splatting (3DGS) is a transformative technique with profound implications on novel view synthesis and real-time rendering. Given its importance, there have been many attempts to improve its performance. However, with the…
Language-guided 3D scene understanding is important for advancing applications in robotics, AR/VR, and human-computer interaction, enabling models to comprehend and interact with 3D environments through natural language. While 2D…
In this paper, we introduce \textbf{GS-SLAM} that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping (SLAM) system. It facilitates a better balance between efficiency and accuracy. Compared to recent SLAM…
Embedding a language field in a 3D representation enables richer semantic understanding of spatial environments by linking geometry with descriptive meaning. This allows for a more intuitive human-computer interaction, enabling querying or…
Open-vocabulary querying in 3D space is challenging but essential for scene understanding tasks such as object localization and segmentation. Language-embedded scene representations have made progress by incorporating language features into…
3D Gaussian Splatting represents a breakthrough in the field of novel view synthesis. It establishes Gaussians as core rendering primitives for highly accurate real-world environment reconstruction. Recent advances have drastically…
Open-vocabulary panoptic reconstruction is crucial for advanced robotics and simulation. However, existing 3D reconstruction methods, such as NeRF or Gaussian Splatting variants, often struggle to achieve the real-time inference frequency…
Recent advancements in 3D Gaussian Splatting have significantly improved the efficiency and quality of dense semantic SLAM. However, previous methods are generally constrained by limited-category pre-trained classifiers and implicit…
Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. This surge in demand poses significant challenges in optimizing throughput and latency while keeping costs manageable. The Key-Value…
Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to high-resolution…
Transforming a large language model (LLM) into a Vision-Language Model (VLM) can be achieved by mapping the visual tokens from a vision encoder into the embedding space of an LLM. Intriguingly, this mapping can be as simple as a shallow MLP…
Navigating to a designated goal using visual information is a fundamental capability for intelligent robots. To address the practical demands of multi-modal, open-vocabulary goal queries and multi-goal visual navigation, we propose LagMemo,…
3D scene reconstruction and understanding have gained increasing popularity, yet existing methods still struggle to capture fine-grained, language-aware 3D representations from 2D images. In this paper, we present GALA, a novel framework…
Recent advances in vision-language models have made zero-shot navigation feasible, enabling robots to follow natural language instructions without requiring labeling. However, existing methods that explicitly store language vectors in grid…
Long-horizon applications increasingly require large language models (LLMs) to answer queries when relevant evidence is sparse and dispersed across very long contexts. Existing memory systems largely follow two paradigms: explicit…
We introduce ShelfGaussian, an open-vocabulary multi-modal Gaussian-based 3D scene understanding framework supervised by off-the-shelf vision foundation models (VFMs). Gaussian-based methods have demonstrated superior performance and…