Unified 3D Scene Understanding Through Physical World Modeling

• URL: http://arxiv.org/abs/2605.24321v1
• Date: Sat, 23 May 2026 01:01:35 GMT
• Title: Unified 3D Scene Understanding Through Physical World Modeling
• Abstract summary: We present a physical world model for unified 3D understanding and interaction, formulated as a probabilistic graphical model in which nodes represent multimodal scene elements such as RGB, optical flow, and camera pose.<n>3WM outperforms specialized baselines without the need for finetuning by offering precise controllability, strong geometric consistency, and robustness in real-world scenarios.<n>This demonstrates that a unified model can serve as a practical alternative to fragmented task-specific systems, taking a step towards a general-purpose visual world model.
• Score: 10.45277075153122
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding 3D scenes requires flexible combinations of visual reasoning tasks, including depth estimation, novel view synthesis, and object manipulation, all of which are essential for perception and interaction. Existing approaches have typically addressed these tasks in isolation, preventing them from sharing a common representation or transferring knowledge across tasks. A conceptually simpler but practically non-trivial alternative is to unify these diverse tasks into a single model, reducing different tasks from separate training objectives to merely different prompts and allowing for joint training across all datasets. In this work, we present a physical world model for unified 3D understanding and interaction (3WM), formulated as a probabilistic graphical model in which nodes represent multimodal scene elements such as RGB, optical flow, and camera pose. Diverse tasks emerge from different inference pathways through the graph: novel view synthesis from RGB and dense flow prompts, object manipulation from RGB and sparse flow prompts, and depth estimation from RGB and camera conditioning, all zero-shot without task-specific training. 3WM outperforms specialized baselines without the need for finetuning by offering precise controllability, strong geometric consistency, and robustness in real-world scenarios, achieving state-of-the-art performance on NVS and 3D object manipulation. Beyond predefined tasks, the model supports composable inference pathways, such as moving objects aside while navigating a 3D environment, enabling complex geometric reasoning. This demonstrates that a unified model can serve as a practical alternative to fragmented task-specific systems, taking a step towards a general-purpose visual world model.

Related papers

• AFUN: Towards an Affordance Foundation Model for Functionality Understanding [12.890216832485647]
  We present ourmodel, a step towards an affordance foundation model for functionality understanding.<n>We build a large-scale standardized data pipeline that converts heterogeneous robot, human, simulation, and real-world scan data into a shared affordance schema.<n>Ourmodel outperforms all baselines by a large margin across 8 test sets from 4 benchmarks.
  arXiv  Detail & Related papers  (2026-06-01T17:50:16Z)
• Unified Semantic Transformer for 3D Scene Understanding [55.415468022487005]
  We introduce UNITE, a novel feed-forward neural network that unifies a diverse set of 3D semantic tasks within a single model.<n>Our model operates on unseen scenes in a fully end-to-end manner and only takes a few seconds to infer the full 3D semantic geometry.<n>We demonstrate that UNITE achieves state-of-the-art performance on several different semantic tasks and even outperforms task-specific models.
  arXiv  Detail & Related papers  (2025-12-16T12:49:35Z)
• Object-X: Learning to Reconstruct Multi-Modal 3D Object Representations [114.57192386025373]
  Object-X is a versatile multi-modal 3D representation framework.<n>It can encoding rich object embeddings and decoding them back into geometric and visual reconstructions.<n>It supports a range of downstream tasks, including scene alignment, single-image 3D object reconstruction, and localization.
  arXiv  Detail & Related papers  (2025-06-05T09:14:42Z)
• IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments [56.85804719947]
  We present IAAO, a framework that builds an explicit 3D model for intelligent agents to gain understanding of articulated objects in their environment through interaction.<n>We first build hierarchical features and label fields for each object state using 3D Gaussian Splatting (3DGS) by distilling mask features and view-consistent labels from multi-view images.<n>We then perform object- and part-level queries on the 3D Gaussian primitives to identify static and articulated elements, estimating global transformations and local articulation parameters along with affordances.
  arXiv  Detail & Related papers  (2025-04-09T12:36:48Z)
• SIGHT: Synthesizing Image-Text Conditioned and Geometry-Guided 3D Hand-Object Trajectories [124.24041272390954]
  Modeling hand-object interaction priors holds significant potential to advance robotic and embodied AI systems.<n>We introduce SIGHT, a novel task focused on generating realistic and physically plausible 3D hand-object interaction trajectories from a single image.<n>We propose SIGHT-Fusion, a novel diffusion-based image-text conditioned generative model that tackles this task by retrieving the most similar 3D object mesh from a database.
  arXiv  Detail & Related papers  (2025-03-28T20:53:20Z)
• Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
  We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns. A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
  arXiv  Detail & Related papers  (2024-06-17T07:43:53Z)
• 3D Neural Embedding Likelihood: Probabilistic Inverse Graphics for Robust 6D Pose Estimation [50.15926681475939]
  Inverse graphics aims to infer the 3D scene structure from 2D images. We introduce probabilistic modeling to quantify uncertainty and achieve robustness in 6D pose estimation tasks. 3DNEL effectively combines learned neural embeddings from RGB with depth information to improve robustness in sim-to-real 6D object pose estimation from RGB-D images.
  arXiv  Detail & Related papers  (2023-02-07T20:48:35Z)
• Beyond RGB: Scene-Property Synthesis with Neural Radiance Fields [32.200557554874784]
  This paper provides a new approach to scene understanding, by leveraging the recent progress on implicit 3D representation and neural rendering. Building upon the great success of Neural Radiance Fields (NeRFs), we introduce Scene-Property Synthesis with NeRF. We facilitate addressing a variety of scene understanding tasks under a unified framework, including semantic segmentation, surface normal estimation, reshading, keypoint detection, and edge detection.
  arXiv  Detail & Related papers  (2022-06-09T17:59:50Z)

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.