awesome-3d-diffusion
github.com/cwchenwang/awesome-3d-diffusion ↗A collection of papers on diffusion models for 3D generation.
1.3k
GitHub Stars
314
Curated Resources
5
Categories
5 hours ago
Last Refreshed
2D Diffusion with Pretraining2D Diffusion without PretrainingDiffusion in 3D SpaceNovel RepresentationsDiffusion for Motion
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me image-to-3d resources from awesome-3d-diffusion"
Installation instructions →What's inside
2D Diffusion with Pretraining
- 360◦ Reconstruction From a Single Image Using Space Carved OutpaintingImage-to-3D
- 3D Paintbrush: Local Stylization of 3D Shapes with Cascaded Score Distillation3D Editing
- AGG: Amortized Generative 3D Gaussians for Single Image to 3DImage-to-3D
- Anything 3D: Towards Single-view Anything Reconstruction in the WildHuman and Animal
- A Quantitative Evaluation of Score Distillation Sampling Based Text-to-3DCompositional or Scene Generation
- ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image CollectionsHuman and Animal
2D Diffusion without Pretraining
- 3D-aware Image Generation using 2D Diffusion Models3D Objects
- 3DDesigner: Towards Photorealistic 3D Object Generation and Editing with Text-guided Diffusion Models3D Objects
- Consistent View Synthesis with Pose-Guided Diffusion Models3D Scenes
- DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Models3D Scenes
- Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision3D Objects
- DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model3D Objects
Diffusion in 3D Space
- 3DGen: Triplane Latent Diffusion for Textured Mesh GenerationTriplane
- 3D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion ModelsLatent Representation
- 3D Neural Field Generation using Triplane DiffusionTriplane
- 3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion ModelsLatent Representation
- 3d shape generation and completion through point-voxel diffusionPoint Cloud, Meshs, Volumes
- A Diffusion-ReFinement Model for Sketch-to-Point ModelingPoint Cloud, Meshs, Volumes
Novel Representations
Diffusion for Motion
- AAMDM: Accelerated Auto-regressive Motion Diffusion ModelHuman Motion
- A Unified Framework for Multimodal, Multi-Part Human Motion SynthesisHuman Motion
- CG-HOI: Contact-Guided 3D Human-Object Interaction GenerationHuman Motion
- Controllable Group Choreography using Contrastive DiffusionHuman Motion
- Controllable Motion Diffusion ModelHuman Motion
- Controllable Motion Synthesis and Reconstruction with Autoregressive Diffusion ModelsHuman Motion
Showing a sample of 314 resources. View the full list on GitHub →