Related papers: M3: 3D-Spatial MultiModal Memory

3D scene representations have gained immense popularity in recent years. Methods that use Neural Radiance fields are versatile for traditional tasks such as novel view synthesis. In recent times, some work has emerged that aims to extend…

We introduce Referring 3D Gaussian Splatting Segmentation (R3DGS), a new task that aims to segment target objects in a 3D Gaussian scene based on natural language descriptions, which often contain spatial relationships or object attributes.…

Despite encouraging progress in 3D scene understanding, it remains challenging to develop an effective Large Multi-modal Model (LMM) that is capable of understanding and reasoning in complex 3D environments. Most previous methods typically…

3D mapping in dynamic environments poses a challenge for modern researchers in robotics and autonomous transportation. There are no universal representations for dynamic 3D scenes that incorporate multimodal data such as images, point…

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…

Over the past year, 3D Gaussian Splatting (3DGS) has received significant attention for its ability to represent 3D scenes in a perceptually accurate manner. However, it can require a substantial amount of storage since each splat's…

We present MS-Splatting -- a multi-spectral 3D Gaussian Splatting (3DGS) framework that is able to generate multi-view consistent novel views from images of multiple, independent cameras with different spectral domains. In contrast to…

Mirror-containing environments pose unique challenges for 3D reconstruction and novel view synthesis (NVS), as reflective surfaces introduce view-dependent distortions and inconsistencies. While cutting-edge methods such as Neural Radiance…

Dynamic scene reconstruction poses a persistent challenge in 3D vision. Deformable 3D Gaussian Splatting has emerged as an effective method for this task, offering real-time rendering and high visual fidelity. This approach decomposes a…

Three-dimensional reconstruction in scenes with extreme depth variations remains challenging due to inconsistent supervisory signals between near-field and far-field regions. Existing methods fail to simultaneously address inaccurate depth…

We present a novel approach for 3D indoor scene reconstruction that combines 3D Gaussian Splatting (3DGS) with mesh representations. We use meshes for the room layout of the indoor scene, such as walls, ceilings, and floors, while employing…

We introduce MVSplat, an efficient model that, given sparse multi-view images as input, predicts clean feed-forward 3D Gaussians. To accurately localize the Gaussian centers, we build a cost volume representation via plane sweeping, where…

Sparse-view synthesis remains a challenging problem due to the difficulty of recovering accurate geometry and appearance from limited observations. While recent advances in 3D Gaussian Splatting (3DGS) have enabled real-time rendering with…

The emergence of neural representations has revolutionized our means for digitally viewing a wide range of 3D scenes, enabling the synthesis of photorealistic images rendered from novel views. Recently, several techniques have been proposed…

Multi-camera 3D object detection (MC3D) has attracted increasing attention with the growing deployment of multi-sensor physical agents, such as robots and autonomous vehicles. However, MC3D models still struggle to generalize to unseen…

The problem of 3D reconstruction from posed images is undergoing a fundamental transformation, driven by continuous advances in 3D Gaussian Splatting (3DGS). By modeling scenes explicitly as collections of 3D Gaussians, 3DGS enables…

Novel view synthesis has shown rapid progress recently, with methods capable of producing increasingly photorealistic results. 3D Gaussian Splatting has emerged as a promising method, producing high-quality renderings of scenes and enabling…

We present the first application of 3D Gaussian Splatting in monocular SLAM, the most fundamental but the hardest setup for Visual SLAM. Our method, which runs live at 3fps, utilises Gaussians as the only 3D representation, unifying the…

Masked Modeling (MM) has demonstrated widespread success in various vision challenges, by reconstructing masked visual patches. Yet, applying MM for large-scale 3D scenes remains an open problem due to the data sparsity and scene…

Effective embodied exploration requires agents to accumulate and retain spatial knowledge over time. However, existing scene representations, such as discrete scene graphs or static view-based snapshots, lack \textit{post-hoc…