Towards Spatio-Temporal World Scene Graph Generation from Monocular Videos

• URL: http://arxiv.org/abs/2603.13185v1
• Date: Fri, 13 Mar 2026 17:18:03 GMT
• Title: Towards Spatio-Temporal World Scene Graph Generation from Monocular Videos
• Abstract summary: We introduce ActionGenome4D, a dataset that upgrades Action Genome videos into 4D scenes via feed-forward 3D reconstruction.<n>We then formalize World Scene Graph Generation (WSGG), the task of constructing a world scene graph at each timestamp.<n>We propose three complementary methods, each exploring a different inductive bias for reasoning about unobserved objects.
• Score: 17.190262848866396
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Spatio-temporal scene graphs provide a principled representation for modeling evolving object interactions, yet existing methods remain fundamentally frame-centric: they reason only about currently visible objects, discard entities upon occlusion, and operate in 2D. To address this, we first introduce ActionGenome4D, a dataset that upgrades Action Genome videos into 4D scenes via feed-forward 3D reconstruction, world-frame oriented bounding boxes for every object involved in actions, and dense relationship annotations including for objects that are temporarily unobserved due to occlusion or camera motion. Building on this data, we formalize World Scene Graph Generation (WSGG), the task of constructing a world scene graph at each timestamp that encompasses all interacting objects in the scene, both observed and unobserved. We then propose three complementary methods, each exploring a different inductive bias for reasoning about unobserved objects: PWG (Persistent World Graph), which implements object permanence via a zero-order feature buffer; MWAE (Masked World Auto-Encoder), which reframes unobserved-object reasoning as masked completion with cross-view associative retrieval; and 4DST (4D Scene Transformer), which replaces the static buffer with differentiable per-object temporal attention enriched by 3D motion and camera-pose features. We further design and evaluate the performance of strong open-source Vision-Language Models on the WSGG task via a suite of Graph RAG-based approaches, establishing baselines for unlocalized relationship prediction. WSGG thus advances video scene understanding toward world-centric, temporally persistent, and interpretable scene reasoning.

Related papers

• StemVLA:An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation [6.0744834626758495]
  StemVLA is a novel framework that explicitly incorporates both future-oriented 3D spatial knowledge and historical 4D representations into action prediction.<n>We show that StemVLA significantly improves long-horizon task success and state-of-the-art performance on the CALVIN ABC-D benchmark [46], achieving an average sequence length of XXX.
  arXiv  Detail & Related papers  (2026-02-27T06:43:37Z)
• Articulated 3D Scene Graphs for Open-World Mobile Manipulation [55.97942733699124]
  We present MoMa-SG, a framework for building semantic-kinematic 3D scene graphs of articulated scenes.<n>We estimate articulation models using a novel unified twist estimation formulation.<n>We also introduce the novel Arti4D-Semantic dataset.
  arXiv  Detail & Related papers  (2026-02-18T10:40:35Z)
• MagicWorld: Interactive Geometry-driven Video World Exploration [30.475628938909242]
  We propose MagicWorld, an interactive video world model that integrates 3D geometric priors and historical retrieval.<n>We introduce the Action-Guided 3D Geometry Module (AG3D), which constructs a point cloud from the first frame of each interaction.<n>We further propose History Cache Retrieval (HCR) mechanism, which retrieves relevant historical frames during generation and injects them as conditioning signals.
  arXiv  Detail & Related papers  (2025-11-24T08:41:28Z)
• Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning [24.17324180628543]
  We propose a unified framework for Open-World 3D Scene Graph Generation with Retrieval-Augmented Reasoning.<n>Our method integrates Vision-Language Models (VLMs) with retrieval-based reasoning to support multimodal exploration and language-guided interaction.<n>We evaluate our method on 3DSSG and Replica benchmarks across four tasks-scene question answering, visual grounding, instance retrieval, and task planning-demonstrating robust generalization and superior performance in diverse environments.
  arXiv  Detail & Related papers  (2025-11-08T07:37:29Z)
• Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description [56.69740649781989]
  3D scene understanding is a long-standing challenge in computer vision and a key component in enabling mixed reality, wearable computing, and embodied AI.<n>We introduce Articulate3D, an expertly curated 3D dataset featuring high-quality manual annotations on 280 indoor scenes.<n>We also present USDNet, a novel unified framework capable of simultaneously predicting part segmentation along with a full specification of motion attributes for articulated objects.
  arXiv  Detail & Related papers  (2024-12-02T11:33:55Z)
• Local-Global Information Interaction Debiasing for Dynamic Scene Graph Generation [51.92419880088668]
  We propose a novel DynSGG model based on multi-task learning, DynSGG-MTL, which introduces the local interaction information and global human-action interaction information. Long-temporal human actions supervise the model to generate multiple scene graphs that conform to the global constraints and avoid the model being unable to learn the tail predicates.
  arXiv  Detail & Related papers  (2023-08-10T01:24:25Z)
• Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment [71.16699226211504]
  We propose to learn fine-grained action features that are invariant to the viewpoints by aligning egocentric and exocentric videos in time. To this end, we propose AE2, a self-supervised embedding approach with two key designs. For evaluation, we establish a benchmark for fine-grained video understanding in the ego-exo context.
  arXiv  Detail & Related papers  (2023-06-08T19:54:08Z)
• BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects [89.2314092102403]
  We present a near real-time method for 6-DoF tracking of an unknown object from a monocular RGBD video sequence. Our method works for arbitrary rigid objects, even when visual texture is largely absent.
  arXiv  Detail & Related papers  (2023-03-24T17:13:49Z)
• 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)
• A Graph Attention Spatio-temporal Convolutional Network for 3D Human Pose Estimation in Video [7.647599484103065]
  We improve the learning of constraints in human skeleton by modeling local global spatial information via attention mechanisms. Our approach effectively mitigates depth ambiguity and self-occlusion, generalizes to half upper body estimation, and achieves competitive performance on 2D-to-3D video pose estimation.
  arXiv  Detail & Related papers  (2020-03-11T14:54:40Z)

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.