3D 生成

Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

TripoSR: Fast 3D Object Reconstruction from a Single Image

Amagine3D: From hardware requirements to editable 3D designs

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model

[NeurIPS 2025] PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

🌍 WorldGen - Generate Any 3D Scene in Seconds

[ICLR'24] Official PyTorch Implementation of Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors

📦Portable package for running Hunyuan3D 2.0/2.1 on Windows. | 混元 3D 2.0/2.1 整合包

Roblox Foundation Model for 3D Intelligence

[NeurIPS 2025] Direct3D‑S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

AssetFurnace: the most complete open-source image-to-3D pipeline (Oct 2026). Prompt or picture → textured, rigged, animated game character, locally on Apple Silicon or NVIDIA. Pixal3D, TRELLIS.2, Hunyuan3D, SF3D, auto-rig and 21 moves. For indie game devs and 3D artists. Free, Apache-2.0.

[CVPR 2025 Highlight] 3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion

Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction (ICCV 2025)

Generate large-scale explorable 3D scenes with high-quality panorama videos from a single image or text prompt.

A Collection of Papers and Codes for CVPR2026/CVPR2025/ICCV2025/CVPR2024/ECCV2026/ECCV2024 AIGC

(ICLR2026) ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation

[CVPR 2026] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

[NeurIPS 2025 Spotlight] A Native Multimodal LLM for 3D Generation and Understanding

[ICCV 2025 & TPAMI] VistaDream: Sampling multiview consistent images for single-view scene reconstruction

Agentic 3D Modeling with Procedural Control — turns a text prompt into an editable parametric program, with optional per-part materials and articulation.

PhysX: Physical-Grounded 3D Asset Generation (NeurIPS 2025, Spotlight)

A curated list of papers and open-source resources focused on 3D AIGC.

The official implementation of "GaussianCity: Generative Gaussian Splatting for Unbounded 3D City Generation". (CVPR 2025)

Give your AI agent a 3D body: text or a photo to a rigged GLB avatar, an LLM brain, a Solana wallet and a one-tag embed. Keyless MCP server for Claude, Cursor and Codex. 50k+ models forged.

Official repository for "SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE"