Feeling the Space: Egomotion-Aware Video Representation for Efficient and Accurate 3D Scene Understanding

• URL: http://arxiv.org/abs/2603.17980v1
• Date: Wed, 18 Mar 2026 17:42:49 GMT
• Title: Feeling the Space: Egomotion-Aware Video Representation for Efficient and Accurate 3D Scene Understanding
• Abstract summary: This paper significantly enhances Large Language Models (MLLMs) with egomotion modality data.<n>By grounding visual content in physical egomotion trajectories, Motion-MLLM can reason about absolute scale and spatial relationships across the scene.<n>Compared to state-of-the-art (SOTA) methods based on video frames and explicit 3D data, Motion-MLLM exhibits similar or even higher accuracy with significantly less overhead.
• Score: 9.774606705982874
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent Multimodal Large Language Models (MLLMs) have shown high potential for spatial reasoning within 3D scenes. However, they typically rely on computationally expensive 3D representations like point clouds or reconstructed Bird's-Eye View (BEV) maps, or lack physical grounding to resolve ambiguities in scale and size. This paper significantly enhances MLLMs with egomotion modality data, captured by Inertial Measurement Units (IMUs) concurrently with the video. In particular, we propose a novel framework, called Motion-MLLM, introducing two key components: (1) a cascaded motion-visual keyframe filtering module that leverages both IMU data and visual features to efficiently select a sparse yet representative set of keyframes, and (2) an asymmetric cross-modal fusion module where motion tokens serve as intermediaries that channel egomotion cues and cross-frame visual context into the visual representation. By grounding visual content in physical egomotion trajectories, Motion-MLLM can reason about absolute scale and spatial relationships across the scene. Our extensive evaluation shows that Motion-MLLM makes significant improvements in various tasks related to 3D scene understanding and spatial reasoning. Compared to state-of-the-art (SOTA) methods based on video frames and explicit 3D data, Motion-MLLM exhibits similar or even higher accuracy with significantly less overhead (i.e., 1.40$\times$ and 1.63$\times$ higher cost-effectiveness, respectively).

Related papers

• LAWM-3D: Learning 3D-Aware Latent Actions from Human Videos for Generalizable Robot World Models [64.11117186468533]
  World models enable agents to perform forward rollout and planning without real-world interaction.<n>Most existing LAMs rely on single-view inputs and operate primarily in 2D pixel space.<n>We propose LAWM-3D, which introduces three tightly coupled key designs for learning 3D-aware latent actions.
  arXiv  Detail & Related papers  (2026-08-06T07:47:01Z)
• UniMo: Unifying 2D Video and 3D Human Motion with an Autoregressive Framework [54.337290937468175]
  We propose UniMo, an autoregressive model for joint modeling of 2D human videos and 3D human motions within a unified framework.<n>We show that our method simultaneously generates corresponding videos and motions while performing accurate motion capture.
  arXiv  Detail & Related papers  (2025-12-03T16:03:18Z)
• S$^2$-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance [20.55536735670125]
  3D Visual Grounding (3DVG) focuses on locating objects in 3D scenes based on natural language descriptions.<n>Recent advances in Multi-modal Large Language Models (MLLMs) have motivated research into extending them to 3DVG.<n>We propose S$2$-MLLM, an efficient framework that enhances spatial reasoning in MLLMs through implicit spatial reasoning.
  arXiv  Detail & Related papers  (2025-12-01T03:08:34Z)
• 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)
• AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models [20.05010202296243]
  We introduce Fine-grained 3D Embodied Reasoning, which requires an agent to predict, for each referenced affordance element in a 3D scene, its location, motion type, and motion axis.<n>We propose AffordBot, a novel framework that integrates Multimodal Large Language Models (MLLMs) with a tailored chain-of-thought (CoT) reasoning paradigm.<n>AffordBot achieves state-of-the-art performance, demonstrating strong generalization and physically grounded reasoning with only 3D point cloud input and MLLMs.
  arXiv  Detail & Related papers  (2025-11-13T06:43:00Z)
• REALM: An MLLM-Agent Framework for Open World 3D Reasoning Segmentation and Editing on Gaussian Splatting [16.896443736904356]
  Existing 3D segmentation methods often struggle to interpret ambiguous, reasoning-based instructions.<n>We introduce REALM, an innovative MLLM-agent framework that enables open-world reasoning-based segmentation.<n>Our framework seamlessly supports a range of 3D interaction tasks, including object removal, replacement, and style transfer.
  arXiv  Detail & Related papers  (2025-10-18T08:53:08Z)
• Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence [13.168559963356952]
  We present Spatial-MLLM, a novel framework for visual-based spatial reasoning from purely 2D observations.<n>Our key insight is to unleash the strong structure prior to the feed-forward visual geometry foundation model.<n>A connector then integrates both features into unified visual tokens for enhanced spatial understanding.
  arXiv  Detail & Related papers  (2025-05-29T17:59:04Z)
• Empowering Large Language Models with 3D Situation Awareness [84.12071023036636]
  A key difference between 3D and 2D is that the situation of an egocentric observer in 3D scenes can change, resulting in different descriptions.<n>We propose a novel approach to automatically generate a situation-aware dataset by leveraging the scanning trajectory during data collection.<n>We introduce a situation grounding module to explicitly predict the position and orientation of observer's viewpoint, thereby enabling LLMs to ground situation description in 3D scenes.
  arXiv  Detail & Related papers  (2025-03-29T09:34:16Z)
• MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation [91.94869042117621]
  Reasoning segmentation aims to segment target objects in complex scenes based on human intent and spatial reasoning.<n>Recent multimodal large language models (MLLMs) have demonstrated impressive 2D image reasoning segmentation.<n>We introduce MLLM-For3D, a framework that transfers knowledge from 2D MLLMs to 3D scene understanding.
  arXiv  Detail & Related papers  (2025-03-23T16:40:20Z)
• Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding [19.382210260928776]
  Video-3D LLM treats 3D scenes as dynamic videos and incorporates 3D position encoding into these representations.<n>Our model achieves state-of-the-art performance on several 3D scene understanding benchmarks.
  arXiv  Detail & Related papers  (2024-11-30T14:28:53Z)
• Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model [51.83436609094658]
  We introduce Coarse Correspondences, a simple lightweight method that enhances MLLMs' spatial-temporal reasoning with 2D images as input. Our method uses a lightweight tracking model to identify primary object correspondences between frames in a video or across different image viewpoints. We demonstrate that this simple training-free approach brings substantial gains to GPT4-V/O consistently on four benchmarks.
  arXiv  Detail & Related papers  (2024-08-01T17:57:12Z)
• Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding [61.57847727651068]
  Temporal sentence grounding aims to localize a target segment in an untrimmed video semantically according to a given sentence query. Most previous works focus on learning frame-level features of each whole frame in the entire video, and directly match them with the textual information. We propose a novel Motion- and Appearance-guided 3D Semantic Reasoning Network (MA3SRN), which incorporates optical-flow-guided motion-aware, detection-based appearance-aware, and 3D-aware object-level features.
  arXiv  Detail & Related papers  (2022-03-06T13:57:09Z)

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.