Alternatives and similar repositories for scene-language

Users that are interested in scene-language are comparing it to the libraries listed below

• GGGHSL / GraphDreamer
  [CVPR'24] GraphDreamer: a novel framework of generating compositional 3D scenes from scene graphs.
  ☆180Updated last year
• huanngzh / MIDI
  We have released official implementation in https://github.com/VAST-AI-Research/MIDI-3D
  ☆128Updated 2 months ago
• sunfanyunn / LayoutVLM
  Official code for "LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models" (CVPR 2025)
  ☆77Updated 5 months ago
• haoyi-duan / WorldScore
  Official implementation for WorldScore: A Unified Evaluation Benchmark for World Generation
  ☆99Updated 3 weeks ago
• chenguolin / InstructScene
  [ICLR 2024 spotlight] Official implementation of "InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior".
  ☆116Updated 3 months ago
• 3DTopia / GPTEval3D
  [ CVPR 2024 ] Implementation for "GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation"
  ☆264Updated 11 months ago
• TencentARC / DI-PCG
  Code release of our paper "DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation".
  ☆103Updated last month
• hwjiang1510 / Real3D
  Code for "Real3D: Scaling Up Large Reconstruction Models with Real-World Images"
  ☆170Updated 11 months ago
• HeliosZhao / GenXD
  GenXD: Generating Any 3D and 4D Scenes. ICLR 2025
  ☆196Updated last month
• dreamscene4d / dreamscene4d
  [NeurIPS 2024] DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
  ☆226Updated 7 months ago
• cyw-3d / SAR3D
  Official repository for "SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE"
  ☆146Updated last month
• hzxie / Awesome-3D-Scene-Generation
  A curated list of awesome 3D scene generation papers. (arXiv 2505.05474)
  ☆301Updated this week
• nv-tlabs / L4GM-official
  [NeurIPS 2024] L4GM: Large 4D Gaussian Reconstruction Model
  ☆197Updated 3 months ago
• liuff19 / DreamReward
  [ECCV 2024] DreamReward: Text-to-3D Generation with Human Preference
  ☆141Updated last month
• Haian-Jin / LVSM
  [ICLR 2025 Oral] Official code for "LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias"
  ☆260Updated 2 weeks ago
• GenEx-world / genex
  Generative World Explorer
  ☆143Updated 5 months ago
• sherwinbahmani / tc4d
  TC4D: Trajectory-Conditioned Text-to-4D Generation
  ☆192Updated 7 months ago
• ML-GSAI / MicroDreamer
  Official implementation of "MicroDreamer: Zero-shot 3D Generation in ~20 Seconds by Score-based Iterative Reconstruction".
  ☆120Updated 7 months ago
• liuff19 / Physics3D
  Official implementation of Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion
  ☆200Updated 11 months ago
• DreamScene-Project / DreamScene
  [ECCV2024] DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling
  ☆150Updated 3 months ago
• phyworld / phyworld
  ☆126Updated 4 months ago
• yanqinJiang / Animate3D
  [NeurIPS 2024] Animate3D: Animating Any 3D Model with Multi-view Video Diffusion
  ☆187Updated 6 months ago
• PhyScene / PhyScene
  Code implementation of CVPR 2024 highlight paper "PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI"
  ☆149Updated 6 months ago
• cwchenwang / awesome-4d-generation
  List of papers on 4D Generation.
  ☆272Updated 7 months ago
• xizaoqu / WorldMem
  [ArXiv 2025] WorldMem: Long-term Consistent World Simulation with Memory
  ☆124Updated last week
• tyhuang0428 / DreamPhysics
  [AAAI 2025] DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors
  ☆204Updated 11 months ago
• PhyRecon / PhyRecon
  PhyRecon: Physically Plausible Neural Scene Reconstruction
  ☆151Updated last month
• ashawkey / objaverse_filter
  naive filter of objaverse
  ☆137Updated last year
• sail-sg / Consistent3D
  The official PyTorch implementation of Consistent3D (CVPR 2024)
  ☆80Updated last year
• crockwell / Cap3D
  [NeurIPS 2023] Scalable 3D Captioning with Pretrained Models
  ☆266Updated last year