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

arXiv: https://arxiv.org/abs/2605.13862 · HTML: https://mlsanity.com/paper/2605.13862/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 22 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Builds on (most cited first, 16 of 16)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models](https://mlsanity.com/paper/2301.11445/) (2023)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models](https://mlsanity.com/paper/2502.06608/) (2025)
- [Native and Compact Structured Latents for 3D Generation](https://mlsanity.com/paper/2512.14692/) (2025)
- [PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects](https://mlsanity.com/paper/2308.07391/) (2023)
- [Sonata: Self-Supervised Learning of Reliable Point Representations](https://mlsanity.com/paper/2503.16429/) (2025)
- [Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders](https://mlsanity.com/paper/2412.17808/) (2024)
- [PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers](https://mlsanity.com/paper/2506.05573/) (2025)
- [LATTICE: Democratize High-Fidelity 3D Generation at Scale](https://mlsanity.com/paper/2512.03052/) (2025)
- [Puppeteer: Rig and Animate Your 3D Models](https://mlsanity.com/paper/2508.10898/) (2025)
- [AutoPartGen: Autogressive 3D Part Generation and Discovery](https://mlsanity.com/paper/2507.13346/) (2025)
- [DragAPart: Learning a Part-Level Motion Prior for Articulated Objects](https://mlsanity.com/paper/2403.15382/) (2024)

## Built on by (most cited first, 4 of 4)

- [Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling](https://mlsanity.com/paper/2608.30821/) (2026)
- [Home3D 1.0: A High-Fidelity Image-to-3D Asset Generation System for Interior Design](https://mlsanity.com/paper/2606.27923/) (2026)
- [Point2Part: Unified 3D Partitioning from Point Prompts](https://mlsanity.com/paper/2609.38180/) (2026)
- [HI3D 3.0 (Twinkle3D): Object-specific 3D Asset Generation with High Resolution](https://mlsanity.com/paper/2610.11685/) (2026)

## 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