EI-Part: Explode for Completion and Implode for Refinement
Not on the map. Why?
Abstract (arXiv)
Part-level 3D generation is crucial for various downstream applications, including gaming, film production, and industrial design. However, decomposing a 3D shape into geometrically plausible and meaningful components remains a significant challenge. Previous part-based generation methods often struggle to produce well-constructed parts, exhibiting poor structural coherence, geometric implausibility, inaccuracy, or inefficiency. To address these challenges, we introduce EI-Part, a novel framework specifically designed to generate high-quality 3D shapes with components, characterized by strong structural coherence, geometric plausibility, geometric fidelity, and generation efficiency. We propose utilizing distinct representations at different stages: an Explode state for part completion and an Implode state for geometry refinement. This strategy fully leverages spatial resolution, enabling flexible part completion and fine geometric detail generation. To maintain structural coherence between parts, a self-attention mechanism is incorporated in both exploded and imploded states, facilitating effective information perception and feature fusion among components during generation. Extensive experiments on multiple benchmarks demonstrate that EI-Part efficiently produces semantically meaningful and structurally coherent parts with fine-grained geometric details, achieving state-of-the-art performance in part-level 3D generation. Project page: https://cvhadessun.github.io/EI-Part/
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 57 of its 59 references that are in the map. First posted on arXiv 14 Mar 2026.
Builds on
57 of 59 references.
References · 57
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2023Segment Anythingcited by 8,234
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
- 2022Scalable Diffusion Models with Transformerscited by 6,054
- 2022Flow Matching for Generative Modelingcited by 5,702
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
- 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
- 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
- 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
38 more
- 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
- 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
- 2020Point Transformercited by 1,470
- 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 1,006
- 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
- 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
- 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
- 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
- 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 458
- 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 455
- 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 366
- 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 356
- 20203D-FUTURE: 3D Furniture shape with TextUREcited by 311
- 20223D Neural Field Generation using Triplane Diffusioncited by 274
- 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 259
- 2025TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Modelscited by 213
- 2023XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchiescited by 189
- 2023Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigationcited by 167
- 2024MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformerscited by 144
- 2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
- 2024CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refinercited by 123
- 2025Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridgingcited by 99
- 2024SAMPart3D: Segment Any Part in 3D Objectscited by 97
- 2025PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyondcited by 95
- 2024Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scalecited by 89
- 2025Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modelingcited by 89
- 2025PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformerscited by 84
- 2024PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Modelscited by 62
- 2025OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesioncited by 61
- 2025HoloPart: Generative 3D Part Amodal Segmentationcited by 60
- 2024Meta 3D TextureGen: Fast and Consistent Texture Generation for 3D Objectscited by 52
- 2025Efficient Part-level 3D Object Generation via Dual Volume Packingcited by 48
- 2023SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentationcited by 44
- 2025Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attentioncited by 44
- 2025X-Part: high fidelity and structure coherent shape decompositioncited by 44
- 2025P3-SAM: Native 3D Part Segmentationcited by 43
- 2024Segment Any Meshcited by 37
- 2025BANG: Dividing 3D Assets via Generative Exploded Dynamicscited by 35
50 most cited of 57 All 57 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.