3d-scene-generation 开源项目推荐（27 个）

wgsxm /PartCrafter

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

hzxie /Awesome-3D-Scene-Generation

A curated list of awesome 3D scene generation papers. (IJCV 2026)

VAST-AI-Research /MIDI-3D

[CVPR 2025] MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation

OpenDCAI /OpenWorldLib

高级世界模型统一代码库。

caiyuanhao1998 /Open-DiffusionGS

将高斯泼溅烘焙进扩散去噪器，以实现快速且可扩展的单阶段图像到 3D 生成与重建（ICCV 2025）

SkyworkAI /Matrix-3D

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

Mengmouxu /SceneGen

[3DV 2026] "SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass"

yuhengliu02 /pyramid-discrete-diffusion

[ECCV 2024 Oral] Pyramid Diffusion for Fine 3D Large Scene Generation

huanngzh /MIDI

We have released official implementation in https://github.com/VAST-AI-Research/MIDI-3D

avinashpaliwal /PanoDreamer

[SIGGRAPH Asia 2025] PanoDreamer: Optimization-Based Single Image to 360 3D Scene With Diffusion

avinashpaliwal /RI3D

[ICCV 2025] RI3D: Few-Shot Gaussian Splatting With Repair and Inpainting Diffusion Priors

Graphic-Kiliani /M3DLayout-code

[CVPR 2026 Highlight] M3DLayout-A-Multi-Source-Dataset-of-3D-Indoor-Layouts-and-Structured-Descriptions.

chen-wl20 /SceneCompleter

SceneCompleter: Dense 3D Scene Completion for Generative Novel View Synthesis

zhao-yiqun /RoomDesigner

[3DV 2024] official repo of 3DV paper "RoomDesigner: Encoding Anchor-latents for Style-consistent and Shape-compatible Indoor Scene Generation"

yangzhifeio /MMGDreamer

[AAAI 2025]MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene Generation

hamnaanaa /3D-Scene-Diffusion-Guidance-using-Scene-Graphs

The implementation for "3D Scene Diffusion Guidance using Scene Graphs" paper. A Diffusion Model for Conditional 3D Scene Generation with Classifier-Free Guidance on Scene Graphs

divyanshu-talwar /ShakaLakaBoomBoom

Unity application to convert 2D sketches to 3D models which could be maneuvered around using hand gestures (to a position and orientation of choice) in a 3D scene.

peaes /GeoWorld

[ECCV 2026] GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation

pittisl /infinibench

Code repo for paper: InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexity

Minglin-Chen /Layout2Scene

🚀 Layout2Scene generates 3D scene from human-provided layout and style prompt