PARSE: Part-Aware Relational Spatial Modeling

• URL: http://arxiv.org/abs/2603.07704v1
• Date: Sun, 08 Mar 2026 16:11:18 GMT
• Title: PARSE: Part-Aware Relational Spatial Modeling
• Abstract summary: We present PARSE, a framework that explicitly models how object parts interact to determine feasible and spatially grounded scene configurations.<n>We build PARSE-10K, a dataset of 10,000 3D indoor scenes constructed from real-image layout priors and a curated part-annotated shape database.<n>With this structured, spatially grounded supervision, fine-tuning Qwen3-VL on PARSE-10K yields stronger object-level layout reasoning and more accurate part-level relation understanding.
• Score: 37.44430581571346
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Inter-object relations underpin spatial intelligence, yet existing representations -- linguistic prepositions or object-level scene graphs -- are too coarse to specify which regions actually support, contain, or contact one another, leading to ambiguous and physically inconsistent layouts. To address these ambiguities, a part-level formulation is needed; therefore, we introduce PARSE, a framework that explicitly models how object parts interact to determine feasible and spatially grounded scene configurations. PARSE centers on the Part-centric Assembly Graph (PAG), which encodes geometric relations between specific object parts, and a Part-Aware Spatial Configuration Solver that converts these relations into geometric constraints to assemble collision-free, physically valid scenes. Using PARSE, we build PARSE-10K, a dataset of 10,000 3D indoor scenes constructed from real-image layout priors and a curated part-annotated shape database, each with dense contact structures and a part-level contact graph. With this structured, spatially grounded supervision, fine-tuning Qwen3-VL on PARSE-10K yields stronger object-level layout reasoning and more accurate part-level relation understanding; furthermore, leveraging PAGs as structural priors in 3D generation models leads to scenes with substantially improved physical realism and structural complexity. Together, these results show that PARSE significantly advances geometry-grounded spatial reasoning and supports the generation of physically consistent 3D scenes.

Related papers

• StructureGS: Structure-aware Gaussian Splatting for Articulated Object Reconstruction [4.05635014683931]
  We introduce StructureGS, a reconstruction framework for articulated objects that integrates structure-aware guidance into 3D Gaussian Splatting.<n>Our method achieves state-of-the-art performance in articulated object reconstruction, producing high-quality results with well-defined part geometries.
  arXiv  Detail & Related papers  (2026-07-29T13:18:38Z)
• SDesc3D: Towards Layout-Aware 3D Indoor Scene Generation from Short Descriptions [71.54559024212976]
  3D indoor scene generation conditioned on short textual descriptions provides a promising avenue for interactive 3D environment construction.<n>Existing works suffer from poor physical plausibility and insufficient detail richness in such semantic condensation cases.<n>We propose SDesc3D, a short-text conditioned 3D indoor scene generation framework, that leverages multi-view structural priors and regional functionality implications.
  arXiv  Detail & Related papers  (2026-04-02T12:33:01Z)
• DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising [12.282331512159473]
  We propose DreamPartGen, a framework for semantically grounded, part-aware text-to-3D generation.<n>A co-denoising process enforces mutual geometric consistency, enabling coherent, interpretable text-aligned 3 synthesis.
  arXiv  Detail & Related papers  (2026-03-19T17:58:11Z)
• Interact3D: Compositional 3D Generation of Interactive Objects [31.12099147294145]
  We present a novel framework designed to generate physically plausible interacting 3D compositional objects.<n>Our approach first leverages advanced generative priors to curate high-quality individual assets.<n>To physically compose these assets, we then introduce a robust two-stage composition pipeline.
  arXiv  Detail & Related papers  (2026-03-17T03:21:06Z)
• EI-Part: Explode for Completion and Implode for Refinement [24.68404709805507]
  We introduce EI-Part, a novel framework specifically designed to generate high-quality 3D shapes with components.<n>We propose utilizing distinct representations at different stages: an Explode state for part completion and an Implode state for geometry refinement.<n>To maintain structural coherence between parts, a self-attention mechanism is incorporated in both exploded and imploded states.
  arXiv  Detail & Related papers  (2026-03-14T16:49:37Z)
• IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction [82.53307702809606]
  Humans naturally perceive the geometric structure and semantic content of a 3D world as intertwined dimensions.<n>We propose InstanceGrounded Geometry Transformer (IGGT) to unify the knowledge for both spatial reconstruction and instance-level contextual understanding.
  arXiv  Detail & Related papers  (2025-10-26T14:57:44Z)
• Causal Reasoning Elicits Controllable 3D Scene Generation [35.22855710229319]
  CausalStruct is a novel framework that embeds causal reasoning into 3D scene generation.<n>We construct causal graphs where nodes represent objects and attributes, while edges encode causal dependencies and physical constraints.<n>Our method uses text or images to guide object placement and layout in 3D scenes, with 3D Gaussian Splatting and Score Distillation Sampling improving shape accuracy and rendering stability.
  arXiv  Detail & Related papers  (2025-09-18T01:03:21Z)
• HiScene: Creating Hierarchical 3D Scenes with Isometric View Generation [50.206100327643284]
  HiScene is a novel hierarchical framework that bridges the gap between 2D image generation and 3D object generation.<n>We generate 3D content that aligns with 2D representations while maintaining compositional structure.
  arXiv  Detail & Related papers  (2025-04-17T16:33:39Z)
• TC-SfM: Robust Track-Community-Based Structure-from-Motion [24.956499348500763]
  We propose to exploit high-level information in the scene, i.e., the spatial contextual information of local regions, to guide the reconstruction. A novel structure is proposed, namely, textittrack-community, in which each community consists of a group of tracks and represents a local segment in the scene.
  arXiv  Detail & Related papers  (2022-06-13T01:09:12Z)
• Neural Part Priors: Learning to Optimize Part-Based Object Completion in RGB-D Scans [27.377128012679076]
  We propose to leverage large-scale synthetic datasets of 3D shapes annotated with part information to learn Neural Part Priors. We can optimize over the learned part priors in order to fit to real-world scanned 3D scenes at test time. Experiments on the ScanNet dataset demonstrate that NPPs significantly outperforms state of the art in part decomposition and object completion.
  arXiv  Detail & Related papers  (2022-03-17T15:05:44Z)
• Reconstructing Interactive 3D Scenes by Panoptic Mapping and CAD Model Alignments [81.38641691636847]
  We rethink the problem of scene reconstruction from an embodied agent's perspective. We reconstruct an interactive scene using RGB-D data stream. This reconstructed scene replaces the object meshes in the dense panoptic map with part-based articulated CAD models.
  arXiv  Detail & Related papers  (2021-03-30T05:56:58Z)
• Towards Part-Based Understanding of RGB-D Scans [43.4094489272776]
  We propose the task of part-based scene understanding of real-world 3D environments. From an RGB-D scan of a scene, we detect objects, and for each object predict its decomposition into geometric part masks. We leverage an intermediary part graph representation to enable robust completion as well as building of part priors.
  arXiv  Detail & Related papers  (2020-12-03T17:30:02Z)
• Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image [102.44347847154867]
  We propose a novel formulation that allows to jointly recover the geometry of a 3D object as a set of primitives. Our model recovers the higher level structural decomposition of various objects in the form of a binary tree of primitives. Our experiments on the ShapeNet and D-FAUST datasets demonstrate that considering the organization of parts indeed facilitates reasoning about 3D geometry.
  arXiv  Detail & Related papers  (2020-04-02T17:58:05Z)

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.