Pith. sign in

REVIEW 25 cited by

PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.05573 v1 pith:GLSPBXHA submitted 2025-06-05 cs.CV

PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

classification cs.CV
keywords partcraftergenerationpartscompositionalimagelatentpart-levelstructured
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We introduce PartCrafter, the first structured 3D generative model that jointly synthesizes multiple semantically meaningful and geometrically distinct 3D meshes from a single RGB image. Unlike existing methods that either produce monolithic 3D shapes or follow two-stage pipelines, i.e., first segmenting an image and then reconstructing each segment, PartCrafter adopts a unified, compositional generation architecture that does not rely on pre-segmented inputs. Conditioned on a single image, it simultaneously denoises multiple 3D parts, enabling end-to-end part-aware generation of both individual objects and complex multi-object scenes. PartCrafter builds upon a pretrained 3D mesh diffusion transformer (DiT) trained on whole objects, inheriting the pretrained weights, encoder, and decoder, and introduces two key innovations: (1) A compositional latent space, where each 3D part is represented by a set of disentangled latent tokens; (2) A hierarchical attention mechanism that enables structured information flow both within individual parts and across all parts, ensuring global coherence while preserving part-level detail during generation. To support part-level supervision, we curate a new dataset by mining part-level annotations from large-scale 3D object datasets. Experiments show that PartCrafter outperforms existing approaches in generating decomposable 3D meshes, including parts that are not directly visible in input images, demonstrating the strength of part-aware generative priors for 3D understanding and synthesis. Code and training data will be released.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 25 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. UnfoldArt: Zero-Shot Recovery of Full Articulated 3D Objects from Text or Image

    cs.CV 2026-06 unverdicted novelty 7.0

    UnfoldArt uses a two-round structured debate between high-level semantic agents and low-level parameter agents, grounded in generated video, to infer articulation and reconstruct full articulated 3D objects including ...

  2. UnfoldArt: Zero-Shot Recovery of Full Articulated 3D Objects from Text or Image

    cs.CV 2026-06 unverdicted novelty 7.0

    UnfoldArt uses multi-agent debate grounded in vision-language and video models to infer articulation parameters and reconstruct full 3D objects including occluded parts from text or image inputs.

  3. 3D-PLOT-LLM: Part-Level Object Tokens for 3D Large Language Models

    cs.CV 2026-06 unverdicted novelty 7.0

    By inserting per-region markers and reserved vocabulary tokens before frozen encoder patches and refining them via MSR, 3D-PLOT-LLM adds part-level addressing to 3D LLMs, outperforming baselines on PartVerse-QA and 3D...

  4. 3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image

    cs.CV 2026-04 unverdicted novelty 7.0

    3D-Fixer performs in-place 3D asset completion from single-view partial point clouds via coarse-to-fine generation with ORFA conditioning, plus a new ARSG-110K dataset, to achieve higher geometric accuracy than MIDI a...

  5. ART: Articulated Reconstruction Transformer

    cs.CV 2025-12 unverdicted novelty 7.0

    ART is a category-agnostic transformer that maps sparse multi-state RGB images to per-part 3D geometry, texture, and articulation parameters via learnable part slots.

  6. PartDiffuser: Part-wise 3D Mesh Generation via Discrete Diffusion

    cs.CV 2025-11 unverdicted novelty 7.0

    PartDiffuser is a semi-autoregressive discrete diffusion framework that generates high-fidelity 3D meshes from point clouds by combining inter-part autoregression with intra-part parallel diffusion using a part-aware ...

  7. EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning

    cs.CV 2026-07 conditional novelty 6.0

    An end-to-end 3D editing framework achieves high-fidelity local edits from coarse bounding boxes and 2D image prompts using region-aware loss reweighting and a large-scale parts-derived training dataset.

  8. ShellMaker: Language-Guided Exterior Completion under Structural Constraints

    cs.CV 2026-06 unverdicted novelty 6.0

    ShellMaker generates complete building exteriors from scaffolds and style prompts via parametric roofs, LLM prompt refinement, material retrieval, and geometry-aware assembly while preserving structural constraints.

  9. Fishbone: From One 3D Asset to a Million Controllable Edits

    cs.CV 2026-05 unverdicted novelty 6.0

    Fishbone introduces a unified rib-spine representation computed via adaptive heat method, iso-contour ribs, and geometry-aware spine that enables real-time parametric deformation, reduced-space simulation, and animati...

  10. PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects

    cs.CV 2026-05 unverdicted novelty 6.0

    PhysX-Omni unifies simulation-ready 3D asset generation across rigid, deformable, and articulated objects via a new geometry representation, the PhysXVerse dataset, and the PhysX-Bench evaluation suite.

  11. Pixal3D: Pixel-Aligned 3D Generation from Images

    cs.CV 2026-05 unverdicted novelty 6.0

    Pixal3D performs pixel-aligned 3D generation from images via back-projected multi-scale feature volumes, achieving fidelity close to reconstruction while supporting multi-view and scene synthesis.

  12. PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World

    cs.CV 2026-05 unverdicted novelty 6.0

    PhysForge generates physics-grounded 3D assets via a VLM-planned Hierarchical Physical Blueprint and a KineVoxel Injection diffusion model, backed by the new PhysDB dataset of 150,000 annotated assets.

  13. FurnSet: Exploiting Repeats for 3D Scene Reconstruction

    cs.CV 2026-04 unverdicted novelty 6.0

    FurnSet improves single-view 3D scene reconstruction by using per-object CLS tokens and set-aware self-attention to group and jointly reconstruct repeated object instances, with added scene-object conditioning and lay...

  14. PhyMix: Towards Physically Consistent Single-Image 3D Indoor Scene Generation with Implicit--Explicit Optimization

    cs.CV 2026-04 unverdicted novelty 6.0

    PhyMix unifies a new multi-aspect physics evaluator with implicit policy optimization and explicit test-time correction to produce single-image 3D indoor scenes that are both visually faithful and physically plausible.

  15. UniRecGen: Unifying Multi-View 3D Reconstruction and Generation

    cs.CV 2026-04 unverdicted novelty 6.0

    UniRecGen unifies reconstruction and generation via shared canonical space and disentangled cooperative learning to produce complete, consistent 3D models from sparse views.

  16. Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models

    cs.CV 2025-11 unverdicted novelty 6.0

    A feed-forward video latent transformer that predicts time-varying 3D Gaussian primitives from one image to produce controllable 4D scenes with appearance, geometry, and motion.

  17. SceneConductor: 3D Scene Generation from a Single Image with Multi-Agent Orchestration

    cs.CV 2026-06 unverdicted novelty 5.0

    SceneConductor decomposes single-image 3D scene generation into initialization, environment construction, and multi-agent refinement stages with a geometry-aware layout predictor trained on sparse geometric priors fro...

  18. WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes

    cs.CV 2026-05 unverdicted novelty 5.0

    WorldAct activates monolithic 3D worlds into interactive scenes via multimodal agent-guided decomposition, geometrically aligned mesh reconstruction, and 3D inpainting.

  19. From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation

    cs.GR 2026-04 unverdicted novelty 5.0

    The paper surveys 3D asset generation methods and organizes them around the full production pipeline to assess which outputs meet engine-level requirements for interactive applications.

  20. STEP-Parts: Geometric Partitioning of Boundary Representations for Large-Scale CAD Processing

    cs.GR 2026-04 unverdicted novelty 5.0

    STEP-Parts produces tessellation-robust geometric part labels from STEP B-Reps by deterministic merging of same-primitive faces, enabling consistent supervision on 180k+ models.

  21. Home3D 1.0: A High-Fidelity Image-to-3D Asset Generation System for Interior Design

    cs.CV 2026-06 unverdicted novelty 4.0

    Home3D 1.0 is a four-module system using latent SDFs, flow-matching DiTs, MatWeaver, and PartVAE to generate decomposable 3D assets with PBR materials from single images.

  22. Home3D 1.0: A High-Fidelity Image-to-3D Asset Generation System for Interior Design

    cs.CV 2026-06 unverdicted novelty 4.0

    Home3D 1.0 describes a four-module image-to-3D system using latent SDF, flow-matching, texture fields, material retrieval, and part-specific VAEs to produce meshes with PBR materials and decomposable components.

  23. From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation

    cs.GR 2026-04 unverdicted novelty 4.0

    The paper surveys 3D content generation literature using a taxonomy of asset types and production stages to evaluate progress toward engine-ready assets.

  24. Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation

    cs.GR 2026-04 unverdicted novelty 4.0

    Seed3D 2.0 advances 3D content generation via a coarse-to-fine geometry pipeline, unified PBR material model, and simulation-ready scene tools, reporting 69-89.9% win rates over commercial systems in human studies.

  25. OpenWorldLib: A Unified Codebase and Definition of Advanced World Models

    cs.CV 2026-04 unverdicted novelty 4.0

    OpenWorldLib offers a standardized codebase and definition for world models that combine perception, interaction, and memory to understand and predict the world.