Awesome-AIGC4AEC

Collecting papers about potential AIGC applications in the AEC industry.

This is an awesome list of potential AIGC applications in the AEC industry. Wish it could be helpful for both academia and industry. (Still updating)

Please feel free to pull requests to add new resources or open issues for questions, discussion and collaborations.

AEC AIGC Agents & Projects

High-impact foundation models, agentic tools, and open-source 3D generation projects with direct potential for AEC design, visualization, modeling, and world-building workflows.

• GPT-6 Astra: OpenAI's frontier agentic model, demonstrated modeling a house in Blender and turning it into a walkable Unreal Engine 5 scene for design exploration and client preview. [Project]

• Blender MCP: A widely adopted MCP integration that lets LLM agents control Blender for 3D modeling, scene editing, rendering, and asset-generation workflows. [Project] [Code]

• Hunyuan3D-2: Tencent's high-resolution text/image-to-3D asset generation system with geometry and texture generation for production-oriented 3D content creation. [Project] [Code]

• TRELLIS.2: Microsoft's native and compact structured-latent framework for high-quality 3D generation, providing a strong open-source backbone for image-to-3D and downstream design workflows. [Code]

• threestudio: A unified and extensible framework for text-to-3D and image-to-3D content generation, widely used for prototyping and integrating generative 3D methods. [Code]

• ComfyUI-3D-Pack: A popular 3D extension suite for ComfyUI that integrates mesh, UV texture, 3D Gaussian Splatting, NeRF, and multiple image-to-3D generation models into node-based workflows. [Code]

• HunyuanWorld: Tencent's open-source 3D world generation project for creating immersive, explorable, and interactive 3D environments from text or images. [Project] [Code]

Object Scale

Mesh Design

• Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models (ECCV'26) [Paper]

• DiffGI: Differentiable Geometry Images for High-Fidelity Thin-Shell 3D Generation (ECCV'26) [Project] [Paper]

• ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation (ECCV'26) [Project] [Paper]

• Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention (ECCV'26) [Paper]

• SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation (ECCV'26) [Paper]

• Interact3D: Compositional 3D Generation of Interactive Objects (ECCV'26) [Paper]

• DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising (ECCV'26) [Paper]

• KaiNinja: Extending Native 3D Generators to the Part Level (Arxiv'26) [Project] [Paper]

• SAM3D-Part: Interactive Part Selection and Generation from 3D Objects (Arxiv'26) [Paper] [Code]

• Guiding Image-to-3D Generation with Test-Time Partial Observations (Arxiv'26) [Paper]

• ViSculpt: Visual-Centric Agentic Geometry Editing (Arxiv'26) [Paper]

• Luce: Relightable Gaussians for 3D Asset Generation (Arxiv'26) [Paper]

• Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion (Arxiv'26) [Project] [Paper]

• SemanticSlider3D: Training-Free Continuous Semantic Editing for 3D Objects (Arxiv'26) [Paper]

• ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation (Arxiv'26) [Paper] [Code]

• UMI3D: Robust 3D Generation on Unconstrained Multi-Image Inputs via Simultaneous Focus Cross-Attention Routing (Arxiv'26) [Project] [Paper] [Code]

• Text-Image Conditioned 3D Generation (CVPR'26) [Paper]

• Native and Compact Structured Latents for 3D Generation (CVPR'26) [Paper]

• FullPart: Generating each 3D Part at Full Resolution (ICLR'26) [Paper]

• RelaxFlow: Text-Driven Amodal 3D Generation (ICML'26 spotlight) [Paper]

• PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World (ICML'26) [Paper]

• 3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion (CVPR'25 highlight) [Project] [Paper] [Code]

• Turbo3D: Ultra-fast Text-to-3D Generation (CVPR'25) [Paper]

• Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets (Arxiv'25) [Paper] [Code]

Parametric Design

• DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces (ECCV'26) [Project] [Paper]

• Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precision (ECCV'26) [Paper]

• CIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verification (Arxiv'26) [Paper]

• Procedura: Agentic 3D Modeling with Procedural Control (Arxiv'26) [Project] [Paper]

• aDSL: Agentic 3D Creation via Joint Agent-Program Design (Arxiv'26) [Paper] [Code]

• Test-Time Scaling for CAD Generation via Verifier-Free Consensus Selection (Arxiv'26) [Paper]

• TOOLCAD: Exploring Tool-Using Large Language Models in Text-to-CAD Generation with Reinforcement Learning (ACL'26) [Paper]

• CADMate: Generating CAD Assembly Plan with Geometric Chain-of-Thought and Spatial Physical Rewards (ACL'26) [Paper]

• RA-CAD: Learning Post-Execution Critique for State-Aware Text-to-CAD Generation (Arxiv'26) [Paper]

• TraceCAD: Trace-Guided Repair for Agentic CAD Generation (Arxiv'26) [Paper]

• CADFS: A Big CAD Program Dataset and Framework for Computer-Aided Design with Large Language Models (CVPR'26) [Paper]

• CAD-Refiner: A Unified Framework for CAD Generation and Iterative Editing (CVPR'26) [Paper]

• Bidirectional Query-Driven Generation of Parametric CAD Sketch (CVPR'26) [Paper]

• How Can Large Language Models Help Humans in Design and Manufacturing? (Arxiv'23) [Paper]

Texture Design

• Material Apprentice: Reflecting Process Expertise in Procedural Material Generation (ECCV'26) [Project] [Paper]

• GLOSS: Geometric Local Self-Similarity Learning for Faithful Reference-Guided Texture Fill (Arxiv'26) [Project] [Paper]

• TEXTRIX: Latent Attribute Grid for Native Texture Generation and Beyond (CVPR'26) [Paper]

• NaTex: Seamless Texture Generation as Latent Color Diffusion (CVPR'26) [Paper]

• CaliTex: Geometry-Calibrated Attention for View-Coherent 3D Texture Generation (CVPR'26) [Paper]

• MatLat: Material Latent Space for PBR Texture Generation (CVPR'26) [Project] [Paper]

• StableMaterials: Enhancing Diversity in Material Generation via Semi-Supervised Learning (CVPR'26) [Project] [Paper]

• MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion (ICCV'25 highlight) [Paper]

• Material Anything: Generating Materials for Any 3D Object via Diffusion (CVPR'25) [Paper]

• TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting (CVPR'25) [Project] [Paper]

• UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes (Arxiv'25) [Paper]

• TexGen: Text-Guided 3D Texture Generation (ECCV'24) [Paper]

• Make-it-Real: Unleashing Large Multimodal Model's Ability for Painting 3D Objects with Realistic Materials (Arxiv'24) [Project] [Paper] [Code]

• MaPa: Text-driven Photorealistic Material Painting for 3D Shapes (SIGGRAPH'24) [Project] [Paper]

• DreamPBR: Text-driven Generation of High-resolution SVBRDF with Multi-modal Guidance (Arxiv'24) [Paper]

• FlashTex: Fast Relightable Mesh Texturing with LightControlNet (Arxiv'24) [Project] [Paper]

• Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering (CVPR'24) [Project] [Paper] [Code]

• TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion (Arxiv'24) [Project] [Paper]

• Collaborative Control for Geometry-Conditioned PBR Image Generation (Arxiv'24) [Project] [Paper]

• Single Mesh Diffusion Models with Field Latents for Texture Generation (CVPR'24) [Project] [Paper] [Code]

• Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models (Arxiv'23) [Project] [Paper] [Code]

• Text-Guided Texturing by Synchronized Multi-View Diffusion (Arxiv'23) [Paper] [Code]

• Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation (ICCV'23) [Project] [Paper] [Code]

• TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models (ICCV'23) [Project] [Paper]

• Text2Tex: Text-driven Texture Synthesis via Diffusion Models (ICCV'23) [Project] [Paper] [Code]

• TEXTure: Text-Guided Texturing of 3D Shapes (SIGGRAPH'23) [Project] [Paper] [Code]

• Text2Mesh: Text-Driven Neural Stylization for Meshes (CVPR'22) [Project] [Paper] [Code]

Room Scale

Mesh Design

• GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation (ECCV'26) [Project] [Paper]

• Scene Generation at Absolute Scale: Utilizing Semantic and Geometric Guidance From Text for Accurate and Interpretable 3D Indoor Scene Generation (ECCV'26) [Paper]

• WorldMesh: Generating Navigable Multi-Room 3D Scenes via Mesh-Conditioned Image Diffusion (ECCV'26) [Project] [Paper] [Code]

• InSpace: Structure-Aware 3D Indoor Scene Generation from a Single 360° Image (ECCV'26) [Project] [Paper]

• OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder (ECCV'26) [Paper] [Code]

• GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation (ECCV'26) [Project] [Paper] [Code]

• SpatialCrafter: Single Image World Modeling with Generative 3D Proxies (Arxiv'26) [Project] [Paper]

• I-Scene: 3D Instance Models are Implicit Generalizable Spatial Learners (CVPR'26) [Project] [Paper]

• MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks (CVPR'26) [Paper]

• SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model (CVPR'26) [Project] [Paper]

• Pano3DComposer: Feed-Forward Compositional 3D Scene Generation from Single Panoramic Image (CVPR'26) [Paper]

• TIMI: Training-Free Image-to-3D Multi-Instance Generation with Spatial Fidelity (ICML'26) [Paper]

• HouseCrafter: Lifting Floorplans to 3D Scenes with 2D Diffusion Models (ICCV'25 highlight) [Project] [Paper] [Code]

• SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation (CVPR'25) [Project] [Paper]

• Layout2Scene: 3D Semantic Layout Guided Scene Generation via Geometry and Appearance Diffusion Priors (Arxiv'25) [Paper]

• ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary (CVPR'25) [Paper]

• DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling (ECCV'24) [Paper]

• AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homes (Arxiv'24) [Project] [Paper] [Code]

• Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane (Arxiv'24) [Paper]

• External Knowledge Enhanced 3D Scene Generation from Sketch (Arxiv'24) [Paper]

• DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting (Arxiv'24) [Project] [Paper]

• Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models (ICCV'23) [Project] [Paper] [Code]

• SceneWiz3D: Towards Text-guided 3D Scene Composition (Arxiv'23) [Project] [Paper] [Code]

• Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints (Arxiv'23) [Paper]

Parametric Design

• Roam2Room: A Unified Floorplan-to-Furnished Framework for Controllable Indoor Scene Generation (ECCV'26) [Project] [Paper]

• Taming LLMs for Codematic Indoor Scene Generation (ECCV'26) [Paper]

• SceneOrchestra: Efficient Agentic 3D Scene Synthesis via Full Tool-Call Trajectory Generation (ECCV'26) [Paper]

• NaLA: A 3D Native LLM Layout Agent for High-quality 3D Scene Generation (ECCV'26) [Paper]

• 4DSynth: Controllable Procedural World Synthesis for Dynamic Embodied Simulation (Arxiv'26) [Paper]

• Beyond Placement and Articulation: Usage-Driven Code Scenes for Embodied Interaction (Arxiv'26) [Paper]

• D3D-GEN: Robot-Aware Domain-Grounded Interactive 3D World Generation for Social Robotics (Arxiv'26) [Paper]

• PolyLayout: Hierarchical VLM-Guided Layout Generation Beyond Rectangular Rooms (Arxiv'26) [Paper]

• iARCS: Iterative Agentic RL for Controllable 3D Scene Generation (Arxiv'26) [Paper]

• Global Graph-Validated Optimization for VLM-based 3D Indoor Scene Generation (ECCV'26) [Paper]

• Roomer: Reflective Object-Grounded Model Editing and Repair for 3D Indoor Layout Synthesis (Arxiv'26) [Paper]

• PlanCraft: Sketch, Refine, and Furnish for Architect-Inspired Progressive 3D Residential Scene Generation (Arxiv'26) [Paper]

• Unified Vector Floorplan Generation via Markup Representation (CVPR'26) [Paper]

• SAGE: Scalable Agentic 3D Scene Generation for Embodied AI (CVPR'26) [Project] [Paper]

• Repurposing 3D Generative Model for Autoregressive Layout Generation (CVPR'26) [Paper]

• Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards (ACL'26) [Paper]

• FloorPlan-DeepSeek (FPDS): A Multimodal Approach to Floorplan Generation using Vector-based Next Room Prediction (Arxiv'25) [Paper]

• Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning (Arxiv'25) [Paper]

• Global-Local Tree Search in VLMs for 3D Indoor Scene Generation (CVPR'25) [Paper]

• Text-to-Layout: A Generative Workflow for Drafting Architectural Floor Plans Using LLMs (Arxiv'25) [Paper]

• Language Guided Generation of 3D Embodied AI Environments (CVPR'24) [Project] [Paper] [Code]

• DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis (CVPR'24) [Project] [Paper] [Code]

• InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior (ICLR'24) [Project] [Paper] [Code]

• Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databases (Arxiv'24) [Paper]

• I-Design: Personalized LLM Interior Designer (Arxiv'24) [Project] [Paper]

• LayoutGPT: Compositional Visual Planning and Generation with Large Language Models (NeurIPS'23) [Project] [Paper] [Code]

Texture Design

• SceneHI: High-Resolution 3D-Consistent Scene Texturing with Controllable Illumination (ECCV'26) [Paper]

• RoomPainter: View-Integrated Diffusion for Consistent Indoor Scene Texturing (CVPR'25) [Paper]

• DreamSpace: Dreaming Your Room Space with Text-Driven Panoramic Texture Propagation (VR'24) [Project] [Paper] [Code]

• SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors (CVPR'24) [Project] [Paper] [Code]

• MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion (NeurIPS'23) [Project] [Paper] [Code]

• Text2Scene: Text-Driven Indoor Scene Stylization With Part-Aware Details (CVPR'23) [Paper]

City Scale

Mesh Design

• LivingWorld: Interactive 4D World Generation with Environmental Dynamics (ECCV'26) [Project] [Paper]

• Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States (Arxiv'26) [Project] [Paper]

• OctWorld: Long-Range World-Consistent Video Generation with Octree-Based 3D Mapping (Arxiv'26) [Project] [Paper]

• Map2World: Segment Map Conditioned Text to 3D World Generation (ECCV'26) [Paper]

• WorldAgents: Can Foundation Image Models be Agents for 3D World Models? (ECCV'26) [Project] [Paper]

• ShellMaker: Language-Guided Exterior Completion under Structural Constraints (ECCV'26) [Project] [Paper]

• GS-Voxel: Fitting-Free Structured Latents for Large-Scale 3DGS Generation (Arxiv'26) [Paper]

• StateFlow: Building, Evolving, and Accessing 3D World States for Previsualization (Arxiv'26) [Project] [Paper]

• To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation (Arxiv'26) [Paper]

• WorldClaw: Agentic 3D Open-World Generation at Scale (Arxiv'26) [Paper]

• PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Urban Scenes (CVPR'26) [Paper]

• Extend3D: Town-Scale 3D Generation (CVPR'26) [Paper]

• ScenDi: 3D-to-2D Scene Diffusion Cascades for Urban Generation (CVPR'26) [Paper]

• WonderTurbo: Generating Interactive 3D World in 0.72 Seconds (ICCV'25) [Project] [Paper] [Code]

• HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels (Arxiv'25) [Paper] [Code]

• Controllable 3D Outdoor Scene Generation via Scene Graphs (ICCV'25) [Paper]

• Large Scene Generation with Cube-Absorb Discrete Diffusion (ICCV'25) [Paper]

• XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies (CVPR'24 highlight) [Project] [Paper]

• Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion (CVPR'24 highlight) [Project] [Paper] [Code]

• WonderJourney: Going from Anywhere to Everywhere (CVPR'24) [Project] [Paper] [Code]

• BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation (Arxiv'24) [Paper]

Parametric Design

• CityDreamer: Compositional Generative Model of Unbounded 3D Cities (CVPR'24) [Project] [Paper] [Code]

• SceneX: Procedural Controllable Large-scale Scene Generation via Large-language Models (Arxiv'24) [Project] [Paper] [Code]

• Infinite Photorealistic Worlds using Procedural Generation (CVPR'23) [Project] [Paper] [Code]