awesome-3d-diffusion
A collection of papers on diffusion models for 3D generation.
https://github.com/cwchenwang/awesome-3d-diffusion
Last synced: 15 days ago
JSON representation
-
2D Diffusion without Pretraining
-
3D Objects
- Novel View Synthesis with Diffusion Models
- Generative Novel View Synthesis with 3D-Aware Diffusion Models
- NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion
- 3DDesigner: Towards Photorealistic 3D Object Generation and Editing with Text-guided Diffusion Models
- SparseFusSparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction
- HoloDiffusion: Training a 3D Diffusion Model using 2D Images
- Renderdiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation
- Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision
- 3D-aware Image Generation using 2D Diffusion Models
- Viewset Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Data
- HOLOFUSION: Towards Photo-realistic 3D Generative Modeling
- Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction Model
- DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model
- LRM: Large Reconstruction Model for Single Image to 3D
- WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space
- ViewFusion: Learning Composable Diffusion Models for Novel View Synthesis
- ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Real Image
-
3D Scenes
- Consistent View Synthesis with Pose-Guided Diffusion Models
- Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models
- DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Models
- SemCity: Semantic Scene Generation with Triplane Diffusion
-
-
2D Diffusion with Pretraining
-
3D Editing
- SKED: Sketch-guided Text-based 3D Editing
- Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions
- Instruct 3D-to-3D: Text Instruction Guided 3D-to-3D conversion
- Edit-DiffNeRF: Editing 3D Neural Radiance Fields using 2D Diffusion Model
- Control4D: Dynamic Portrait Editing by Learning 4D GAN from 2D Diffusion-based Editor
- RePaint-NeRF: NeRF Editting via Semantic Masks and Diffusion Models
- DreamEditor: Text-Driven 3D Scene Editing with Neural Fields
- Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset Updates
- ProteusNeRF: Fast Lightweight NeRF Editing using 3D-Aware Image Context
- ED-NeRF: Efficient Text-Guided Editing of 3D Scene using Latent Space NeRF
- 3D Paintbrush: Local Stylization of 3D Shapes with Cascaded Score Distillation
- GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting
- SHAP-EDITOR: Instruction-guided Latent 3D Editing in Seconds
- LatentEditor: Text Driven Local Editing of 3D Scenes
- Free-Editor: Zero-shot Text-driven 3D Scene Editing
- SIGNeRF: Scene Integrated Generation for Neural Radiance Fields
- Efficient-NeRF2NeRF: Streamlining Text-Driven 3D Editing with Multiview Correspondence-Enhanced Diffusion Models
- ReplaceAnything3D: Text-Guided 3D Scene Editing with Compositional Neural Radiance Fields
- View-Consistent 3D Editing with Gaussian Splatting
- Interactive3D: Create What You Want by Interactive 3D Generation
- DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing
- DATENeRF: Depth-Aware Text-based Editing of NeRFs
- 3D Paintbrush: Local Stylization of 3D Shapes with Cascaded Score Distillation
- Inpaint3D: 3D Scene Content Generation using 2D Inpainting Diffusion
- NeRFiller: Completing Scenes via Generative 3D Inpainting
- GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
-
Compositional or Scene Generation
- Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models
- SceneScape: Text-Driven Consistent Scene Generation
- Compositional 3D Scene Generation using Locally Conditioned Diffusion
- Set-the-Scene: Global-Local Training for Generating Controllable NeRF Scenes - Bar et al., Arxiv 2023
- CompoNeRF: Text-guided Multi-object Compositional NeRF with Editable 3D Scene Layout
- Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields
- Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints
- ShowRoom3D: Text to High-Quality 3D Room Generation Using 3D Priors
- SceneWiz3D: Towards Text-guided 3D Scene Composition
- Text2Street: Controllable Text-to-image Generation for Street Views
- A Quantitative Evaluation of Score Distillation Sampling Based Text-to-3D
- Sketch2NeRF: Multi-view Sketch-guided Text-to-3D Generation
- DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling
- DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting
- RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion
- Urban Architect: Steerable 3D Urban Scene Generation with Layout Prior
- DreamScape: 3D Scene Creation via Gaussian Splatting joint Correlation Modeling
- Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting
- REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignment
- VividDream: Generating 3D Scene with Ambient Dynamics
- Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text
- Sketch2Scene: Automatic Generation of Interactive 3D Game Scenes from User's Casual Sketches
- Scene123: One Prompt to 3D Scene Generation via Video-Assisted and Consistency-Enhanced MAE
- VividDreamer: Towards High-Fidelity and Efficient Text-to-3D Generation
- HoloDreamer: Holistic 3D Panoramic World Generation from Text Descriptions
- COMOGen: A Controllable Text-to-3D Multi-object Generation Framework
- DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes
- GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting
-
Human and Animal
- DreamFace: Progressive Generation of Animatable 3D Faces under Text Guidance
- AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control
- DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models
- DreamWaltz: Make a Scene with Complex 3D Animatable Avatars
- ZeroAvatar: Zero-shot 3D Avatar Generation from a Single Image
- AvatarBooth: High-Quality and Customizable 3D Human Avatar Generation
- Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusion
- Anything 3D: Towards Single-view Anything Reconstruction in the Wild
- ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections
- TADA! Text to Animatable Digital Avatars
- Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips
- HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
- AvatarStudio: High-fidelity and Animatable 3D Avatar Creation from Text
- Disentangled Clothed Avatar Generation from Text Descriptions
- SEEAvatar: Photorealistic Text-to-3D Avatar Generation with Constrained Geometry and Appearance
- GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning
- Make-A-Character: High Quality Text-to-3D Character Generation within Minutes
- Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation
- ScoreHMR: Score-Guided Diffusion for 3D Human Recovery
- Generative Proxemics: A Prior for 3D Social Interaction from Images
- Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusion
- Text-Guided Generation and Editing of Compositional 3D Avatars
-
Image-to-3D
- Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting
- NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with $360^{\deg}$ Views
- NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors
- Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures
- RealFusion: 360{\deg} Reconstruction of Any Object from a Single Image - Kyriazi et al., Arxiv 2023
- Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior
- Zero-1-to-3: Zero-shot One Image to 3D Object
- DreamBooth3D: Subject-Driven Text-to-3D Generation
- DreamSparse: Escaping from Plato's Cave with 2D Frozen Diffusion Model Given Sparse Views
- One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization
- Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
- 360◦ Reconstruction From a Single Image Using Space Carved Outpainting
- Customize-It-3D: High-Quality 3D Creation from A Single Image Using Subject-Specific Knowledge Prior
- HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D
- AGG: Amortized Generative 3D Gaussians for Single Image to 3D
- IPDreamer: Appearance-Controllable 3D Object Generation with Image Prompts
- Part123: Part-aware 3D Reconstruction from a Single-view Image
- GECO: Generation Image-to-3D within a Second
- Fourier123: One Image to High-Quality 3D Object Generation with Hybrid Fourier Score Distillation
- Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
- Viewpoint Textual Inversion: Unleashing Novel View Synthesis with Pretrained 2D Diffusion Models
-
Multi-view Diffusion
- MVDream: Multi-view Diffusion for 3D Generation
- MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion
- Wonder3D: Single Image to 3D using Cross-Domain Diffusion
- Text-Guided Texturing by Synchronized Multi-View Diffusion
- EscherNet: A Generative Model for Scalable View Synthesis
- LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation
- SPAD : Spatially Aware Multiview Diffusers
- MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction
- V3D: Video Diffusion Models are Effective 3D Generators
- Controllable Text-to-3D Generation via Surface-Aligned Gaussian Splatting
- FDGaussian: Fast Gaussian Splatting from Single Image via Geometric-aware Diffusion Model
- Isotropic3D: Image-to-3D Generation Based on a Single CLIP Embedding
- SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion
- Generic 3D Diffusion Adapter Using Controlled Multi-View Editing
- VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models
- Envision3D: One Image to 3D with Anchor Views Interpolation
- MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation
- Magic-Boost: Boost 3D Generation with Mutli-View Conditioned Diffusion
- InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
- EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion
- Grounded Compositional and Diverse Text-to-3D with Pretrained Multi-View Diffusion Model
- Multi-view Image Prompted Multi-view Diffusion for Improved 3D Generation
- MVDiff: Scalable and Flexible Multi-View Diffusion for 3D Object Reconstruction from Single-View
- CraftsMan: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner
- Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion
- IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation - Kyriazi et al., Arxiv 2024
- Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle
- BoostDream: Efficient Refining for High-Quality Text-to-3D Generation from Multi-View Diffusion
- Consistent123: Improve Consistency for One Image to 3D Object Synthesis
- Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model
- TOSS:High-quality Text-guided Novel View Synthesis from a Single Image
- Direct2.5: Diverse Text-to-3D Generation via Multi-view 2.5D Diffusion
- ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models
- CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model
- Envision3D: One Image to 3D with Anchor Views Interpolation
- CAT3D: Create Anything in 3D with Multi-View Diffusion Models
- Make-Your-3D: Fast and Consistent Subject-Driven 3D Content Generation
-
Text-to-3D Object Generation
- DreamFusion: Text-to-3D using 2D Diffusion
- Magic3D: High-Resolution Text-to-3D Content Creation
- Score jacobian chaining: Lifting pretrained 2d diffusion models for 3d generation
- Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation
- Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation
- DITTO-NeRF: Diffusion-based Iterative Text To Omni-directional 3D Model
- TextMesh: Generation of Realistic 3D Meshes From Text Prompts
- Text-driven Visual Synthesis with Latent Diffusion Prior
- Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyond
- HiFA: High-fidelity Text-to-3D with Advanced Diffusion Guidance
- ATT3D: Amortized Text-to-3D Object Synthesis
- PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation
- ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation
- EfficientDreamer: High-Fidelity and Robust 3D Creation via Orthogonal-view Diffusion Prior
- SweetDreamer: Aligning Geometric Priors in 2D Diffusion for Consistent Text-to-3D
- LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes
- HyperDreamer: Hyper-Realistic 3D Content Generation and Editing from a Single Image
- RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D
- Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors
- Sherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D Prior
- DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling
- UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generation
- Stable Score Distillation for High-Quality 3D Generation
- Text-Image Conditioned Diffusion for Consistent Text-to-3D Generation
- Retrieval-Augmented Score Distillation for Text-to-3D Generation
- HexaGen3D: StableDiffusion is just one step away from Fast and Diverse Text-to-3D Generation
- BrightDreamer: Generic 3D Gaussian Generative Framework for Fast Text-to-3D Synthesis
- DreamReward: Text-to-3D Generation with Human Preference
- DreamFlow: High-Quality Text-to-3D Generation by Approximating Probability Flow
- LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesis
- DreamPolisher: Towards High-Quality Text-to-3D Generation via Geometric Diffusion
- VP3D: Unleashing 2D Visual Prompt for Text-to-3D Generation
- Hash3D: Training-free Acceleration for 3D Generation
- MicroDreamer: Zero-shot 3D Generation in ∼20 Seconds by Score-based Iterative Reconstruction
- SketchDream: Sketch-based Text-to-3D Generation and Editing
- Flow Score Distillation for Diverse Text-to-3D
- Dreamer XL: Towards High-Resolution Text-to-3D Generation via Trajectory Score Matching
- Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication
- DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data
- Text-guided Controllable Mesh Refinement for Interactive 3D Modeling
- ScaleDreamer: Scalable Text-to-3D Synthesis with Asynchronous Score Distillation
- PlacidDreamer: Advancing Harmony in Text-to-3D Generation
- JointDreamer: Ensuring Geometry Consistency and Text Congruence in Text-to-3D Generation via Joint Score Distillation
- DreamDissector: Learning Disentangled Text-to-3D Generation from 2D Diffusion Priors
- Connecting Consistency Distillation to Score Distillation for Text-to-3D Generation
-
Programming Languages
Categories
Sub Categories
Text-to-3D Object Generation
64
Point Cloud, Meshs, Volumes
58
Human Motion
37
Multi-view Diffusion
37
Compositional or Scene Generation
28
3D Editing
26
Human and Animal
22
Image-to-3D
21
Explicit Representation
20
Latent Representation
20
3D Objects
17
Implicit Representation
14
Texturing
12
Triplane
12
3D Gaussians
4
3D Scenes
4