Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation
Not on the map. Why?
Abstract (arXiv)
We present Seed3D 2.0, an advanced 3D content generation system built on Seed3D 1.0, with substantial improvements across generation fidelity, simulation-ready capabilities, and application coverage. For geometry, a coarse-to-fine two-stage pipeline decouples global structure learning from high-frequency detail recovery, while a locality-aware VAE achieves higher spatial compression and more efficient decoding. For texture and material generation, we replace the cascaded pipeline of Seed3D 1.0 with a unified PBR model that directly generates multi-view albedo and metallic-roughness maps, enhanced by Mixture-of-Experts scaling and VLM-based semantic conditioning for improved material precision and visual fidelity. Beyond single-object generation, Seed3D 2.0 introduces a simulation-ready model suite comprising scene layout planning, part-aware decomposition, and training-free articulation generation, enabling coherent scene construction and part-level physical interaction across physics and graphics engines. A large-scale human preference study against five recent commercial models shows that Seed3D 2.0 achieves consistent win rates of 69.0% to 89.9% in textured 3D asset generation. Seed3D 2.0 is available on https://exp.volcengine.com/ark/vision?_vtm_=0.0.c70961.d701978.0&mode=vision&modelId=doubao-seed3d-2-0-260328&tab=Gen3D
Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 16 of its 22 references that are in the map. First posted on arXiv 22 Apr 2026.
Builds on
16 of 22 references.
References · 16
- 2022Flow Matching for Generative Modelingcited by 5,426
- 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
- 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
- 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
- 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
- 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 342
- 2025TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Modelscited by 204
- 2025Native and Compact Structured Latents for 3D Generationcited by 157
- 2023PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objectscited by 115
- 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 108
- 2024Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoderscited by 93
- 2025PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformerscited by 78
4 more
- 2025Puppeteer: Rig and Animate Your 3D Modelscited by 41
- 2025LATTICE: Democratize High-Fidelity 3D Generation at Scalecited by 41
- 2025AutoPartGen: Autogressive 3D Part Generation and Discoverycited by 33
- 2024DragAPart: Learning a Part-Level Motion Prior for Articulated Objectscited by 32
Built on by
Citing papers per year: 2026: 4.
4 papers.
- 2026Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modelingcited by 2
- 2026Home3D 1.0: A High-Fidelity Image-to-3D Asset Generation System for Interior Designcited by 0
- 2026Point2Part: Unified 3D Partitioning from Point Promptscited by 0
- 2026HI3D 3.0 (Twinkle3D): Object-specific 3D Asset Generation with High Resolutioncited by 0
- 2026HI3D 3.0 (Twinkle3D): Object-specific 3D Asset Generation with High Resolution8 Oct 2026
- 2026Point2Part: Unified 3D Partitioning from Point Prompts29 Sep 2026
- 2026Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling31 Aug 2026
- 2026Home3D 1.0: A High-Fidelity Image-to-3D Asset Generation System for Interior Design26 Jun 2026
Similar, not cited
Close in wording, no citation either way
- 2026Gen2Physics: Grounding Generated 3D Meshes in Physics via Multi-View Material Decomposition
- 2025Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets
- 2023DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
- 20243DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion
- 2025Self-Evolving 3D Scene Generation from a Single Image
- 2026From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation
- 2024Structured 3D Latents for Scalable and Versatile 3D Generation
- 2023HyperDreamer: Hyper-Realistic 3D Content Generation and Editing from a Single Image