M3: 3D-Spatial MultiModal Memory

• URL: http://arxiv.org/abs/2503.16413v1
• Date: Thu, 20 Mar 2025 17:59:12 GMT
• Title: M3: 3D-Spatial MultiModal Memory
• Abstract summary: We present 3D Spatial MultiModal Memory (M3), a multimodal memory system designed to retain information about medium-sized static scenes.<n>By integrating 3D Gaussian Splatting techniques with foundation models, M3 builds a multimodal memory capable of rendering feature representations across granularities.
• Score: 24.23518743364405
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present 3D Spatial MultiModal Memory (M3), a multimodal memory system designed to retain information about medium-sized static scenes through video sources for visual perception. By integrating 3D Gaussian Splatting techniques with foundation models, M3 builds a multimodal memory capable of rendering feature representations across granularities, encompassing a wide range of knowledge. In our exploration, we identify two key challenges in previous works on feature splatting: (1) computational constraints in storing high-dimensional features for each Gaussian primitive, and (2) misalignment or information loss between distilled features and foundation model features. To address these challenges, we propose M3 with key components of principal scene components and Gaussian memory attention, enabling efficient training and inference. To validate M3, we conduct comprehensive quantitative evaluations of feature similarity and downstream tasks, as well as qualitative visualizations to highlight the pixel trace of Gaussian memory attention. Our approach encompasses a diverse range of foundation models, including vision-language models (VLMs), perception models, and large multimodal and language models (LMMs/LLMs). Furthermore, to demonstrate real-world applicability, we deploy M3's feature field in indoor scenes on a quadruped robot. Notably, we claim that M3 is the first work to address the core compression challenges in 3D feature distillation.

Related papers

• M$^3$Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks [19.25978075323521]
  M$3$Eval is the first comprehensive evaluation framework and benchmark for probing different memory dimensions in multi-modal models.<n>We conduct experiments across representative multi-modal models, revealing consistent weaknesses and distinctive behaviors.<n>Our findings highlight memory as a fundamental yet underexplored capability and offer insights for designing more effective memory mechanisms in multi-modal models.
  arXiv  Detail & Related papers  (2026-06-03T15:28:57Z)
• C3G: Learning Compact 3D Representations with 2K Gaussians [55.04010158339562]
  Recent approaches use per-pixel 3D Gaussian Splatting for reconstruction, followed by a 2D-to-3D feature lifting stage for scene understanding.<n>We propose C3G, a novel feed-forward framework that estimates compact 3D Gaussians only at essential spatial locations.
  arXiv  Detail & Related papers  (2025-12-03T17:59:05Z)
• Abstract 3D Perception for Spatial Intelligence in Vision-Language Models [100.13033631690114]
  Vision-language models (VLMs) struggle with 3D-related tasks such as spatial cognition and physical understanding.<n>We introduce SandboxVLM, a framework that leverages abstract bounding boxes to encode geometric structure and physical kinematics for VLM.<n>Our approach consistently improves spatial intelligence, achieving an 8.3% gain on SAT Real compared with baseline methods.
  arXiv  Detail & Related papers  (2025-11-14T04:16:09Z)
• OpenInsGaussian: Open-vocabulary Instance Gaussian Segmentation with Context-aware Cross-view Fusion [89.98812408058336]
  We introduce textbfOpenInsGaussian, an textbfOpen-vocabulary textbfInstance textbfGaussian segmentation framework with Context-aware Cross-view Fusion.<n>OpenInsGaussian achieves state-of-the-art results in open-vocabulary 3D Gaussian segmentation, outperforming existing baselines by a large margin.
  arXiv  Detail & Related papers  (2025-10-21T03:24:12Z)
• MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs [13.678235444299286]
  Multimodal large language models (MLLMs) excel at 2D visual understanding but remain limited in their ability to reason about 3D space.<n>In this work, we leverage large-scale high-quality 3D scene data with open-set annotations to introduce 1) a novel supervised fine-tuning dataset and 2) a new evaluation benchmark, focused on indoor scenes.
  arXiv  Detail & Related papers  (2025-03-17T12:34:22Z)
• Enhancing Vehicle Make and Model Recognition with 3D Attention Modules [1.4999444543328293]
  Vehicle make and model recognition (VMMR) is a crucial component of the Intelligent Transport System.<n>In this study, we implement an attention module to address inter-class similarity and intra-class variation challenges.<n>Our proposed model integrates the attention module into two different locations within the middle section of a convolutional model.
  arXiv  Detail & Related papers  (2025-02-21T11:52:56Z)
• LLMI3D: MLLM-based 3D Perception from a Single 2D Image [77.13869413871028]
  multimodal large language models (MLLMs) excel in general capacity but underperform in 3D tasks.<n>In this paper, we propose solutions for weak 3D local spatial object perception, poor text-based geometric numerical output, and inability to handle camera focal variations.<n>We employ parameter-efficient fine-tuning for a pre-trained MLLM and develop LLMI3D, a powerful 3D perception MLLM.
  arXiv  Detail & Related papers  (2024-08-14T10:00:16Z)
• MonoMM: A Multi-scale Mamba-Enhanced Network for Real-time Monocular 3D Object Detection [9.780498146964097]
  We propose an innovative network architecture, MonoMM, for real-time monocular 3D object detection. MonoMM consists of Focused Multi-Scale Fusion (FMF) and Depth-Aware Feature Enhancement Mamba (DMB) modules. Our method outperforms previous monocular methods and achieves real-time detection.
  arXiv  Detail & Related papers  (2024-08-01T10:16:58Z)
• MVGamba: Unify 3D Content Generation as State Space Sequence Modeling [150.80564081817786]
  We introduce MVGamba, a general and lightweight Gaussian reconstruction model featuring a multi-view Gaussian reconstructor.<n>With off-the-detail multi-view diffusion models integrated, MVGamba unifies 3D generation tasks from a single image, sparse images, or text prompts.<n>Experiments demonstrate that MVGamba outperforms state-of-the-art baselines in all 3D content generation scenarios with approximately only $0.1times$ of the model size.
  arXiv  Detail & Related papers  (2024-06-10T15:26:48Z)
• Matryoshka Multimodal Models [92.41824727506751]
  We propose M3: Matryoshka Multimodal Models, which learns to represent visual content as nested sets of visual tokens. We find that COCO-style benchmarks only need around 9 visual tokens to obtain accuracy similar to that of using all 576 tokens.
  arXiv  Detail & Related papers  (2024-05-27T17:59:56Z)
• VFMM3D: Releasing the Potential of Image by Vision Foundation Model for Monocular 3D Object Detection [80.62052650370416]
  monocular 3D object detection holds significant importance across various applications, including autonomous driving and robotics. In this paper, we present VFMM3D, an innovative framework that leverages the capabilities of Vision Foundation Models (VFMs) to accurately transform single-view images into LiDAR point cloud representations.
  arXiv  Detail & Related papers  (2024-04-15T03:12:12Z)
• Towards Unified 3D Object Detection via Algorithm and Data Unification [70.27631528933482]
  We build the first unified multi-modal 3D object detection benchmark MM- Omni3D and extend the aforementioned monocular detector to its multi-modal version. We name the designed monocular and multi-modal detectors as UniMODE and MM-UniMODE, respectively.
  arXiv  Detail & Related papers  (2024-02-28T18:59:31Z)
• Towards Multimodal Multitask Scene Understanding Models for Indoor Mobile Agents [49.904531485843464]
  In this paper, we discuss the main challenge: insufficient, or even no, labeled data for real-world indoor environments. We describe MMISM (Multi-modality input Multi-task output Indoor Scene understanding Model) to tackle the above challenges. MMISM considers RGB images as well as sparse Lidar points as inputs and 3D object detection, depth completion, human pose estimation, and semantic segmentation as output tasks. We show that MMISM performs on par or even better than single-task models.
  arXiv  Detail & Related papers  (2022-09-27T04:49:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.