Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
Awesome-AIGC-3D
A curated list of awesome AIGC 3D papers
https://github.com/hitcslj/Awesome-AIGC-3D
Last synced: 3 days ago
JSON representation
-
Papers
- SketchDream: Sketch-based Text-to-3D Generation and Editing
- CAT3D: Create Anything in 3D with Multi-View Diffusion Models
- TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts
- Sketch2NeRF: Multi-view Sketch-guided Text-to-3D Generation
- GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation
- ATT3D: Amortized Text-to-3D Object Synthesis
- LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesis
- DreamPolisher: Towards High-Quality Text-to-3D Generation via Geometric Diffusion - lin/DreamPolisher) | [bibtex](./citations/dreampolisher.txt)
- GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image
- 3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation
- DreamFields: Zero-Shot Text-Guided Object Generation with Dream Fields - research/google-research/tree/master/dreamfields) | [bibtex](./citations/dreamfields.txt)
- DreamFusion: Text-to-3D using 2D Diffusion - dreamfusion) | [bibtex](./citations/dreamfusion.txt)
- Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
- Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models
- Magic3D: High-Resolution Text-to-3D Content Creation
- Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation - Lab-SCUT/Fantasia3D) | [bibtex](./citations/fantasia3d.txt)
- Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior - It-3D) | [bibtex](./citations/makeit3d.txt)
- X-Dreamer: Creating High-quality 3D Content by Bridging the Domain Gap Between Text-to-2D and Text-to-3D Generation - xiaoma666/X-Dreamer) | [bibtex](./citations/xdreamer.txt)
- BiDiff: 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
- HexaGen3D: StableDiffusion is just one step away from Fast and Diverse Text-to-3D Generation
- ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation - ml/prolificdreamer) | [bibtex](./citations/prolificdreamer.txt)
- LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching - Research/LucidDreamer) | [bibtex](./citations/luciddreamer-object.txt)
- StableDreamer: Taming Noisy Score Distillation Sampling for Text-to-3D
- CAD: Photorealistic 3D Generation via Adversarial Distillation
- SSD: Stable Score Distillation for High-Quality 3D Generation
- Score Distillation Sampling with Learned Manifold Corrective
- Zero-1-to-3: Zero-shot One Image to 3D Object - columbia/zero123) | [bibtex](./citations/zero123.txt)
- ConRad: Image Constrained Radiance Fields for 3D Generation from a Single Image
- One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization - 2-3-45/One-2-3-45) | [bibtex](./citations/one2345.txt)
- Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
- MVDream: Multi-view Diffusion for 3D Generation
- Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models
- Consistent123: One Image to Highly Consistent 3D Asset Using Case-Aware Diffusion Priors
- Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model - AI-3D/zero123plus) | [bibtex](./citations/zero123++.txt)
- Wonder3D: Single Image to 3D using Cross-Domain Diffusion
- SweetDreamer: Aligning Geometric Priors in 2D Diffusion for Consistent Text-to-3D - 98/SweetDreamer) | [bibtex](./citations/sweetdreamer.txt)
- 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
- Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Views - Zero123) | [bibtex](./citations/cascadeZero123.txt)
- Free3D: Consistent Novel View Synthesis without 3D Representation
- ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation
- AGG: Amortized Generative 3D Gaussians for Single Image to 3D
- DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
- Gsgen: Text-to-3D using Gaussian Splatting
- LRM: Large Reconstruction Model for Single Image to 3D
- Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model
- DMV3D:Denoising Multi-View Diffusion using 3D Large Reconstruction Model
- GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models
- ZeroRF: Fast Sparse View 360° Reconstruction with Zero Pretraining
- DreamBooth3D: Subject-Driven Text-to-3D Generation
- TECA: Text-Guided Generation and Editing of Compositional 3D Avatars
- Control4D: Dynamic Portrait Editing by Learning 4D GAN from 2D Diffusion-based Editor
- Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts
- GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions
- Gaussian Grouping: Segment and Edit Anything in 3D Scenes - grouping) | [bibtex](./citations/gaussian-group.txt)
- SIGNeRF: Scene Integrated Generation for Neural Radiance Fields
- Control3D: Towards Controllable Text-to-3D Generation
- IPDreamer: Appearance-Controllable 3D Object Generation with Image Prompts
- ControlDreamer: Stylized 3D Generation with Multi-View ControlNet
- DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior
- Text2Light: Zero-Shot Text-Driven HDR Panorama Generation
- SceneScape: Text-Driven Consistent Scene Generation
- LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes - cvlab/LucidDreamer) | [bibtext](./citations/luciddreamer-scene.txt)
- Pyramid Diffusion for Fine 3D Large Scene Generation - page/pyramid-discrete-diffusion/) | [bibtext](./citations/pyramid.txt)
- GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs
- RoomDesigner: Encoding Anchor-latents for Style-consistent and Shape-compatible Indoor Scene Generation - yiqun/RoomDesigner) | [bibtext](./citations/roomdesigner.txt)
- AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homes
- Inpaint3D: 3D Scene Content Generation using 2D Inpainting Diffusion
- Text2Immersion: Generative Immersive Scene with 3D Gaussians
- ShowRoom3D: Text to High-Quality 3D Room Generation Using 3D Priors
- ProcTHOR: Large-Scale Embodied AI Using Procedural Generation
- 3D-GPT: Procedural 3D Modeling with Large Language Models
- Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion
- HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting - avatar-release) | [bibtex](./citations/3dgsAvatar.txt)
- TADA! Text to Animatable Digital Avatars
- MAV3d: Text-To-4D Dynamic Scene Generation
- Animate124: Animating One Image to 4D Dynamic Scene
- Consistent4D: Consistent 360° Dynamic Object Generation from Monocular Video
- AnimatableDreamer: Text-Guided Non-rigid 3D Model Generation and Reconstruction with Canonical Score Distillation - dreamer.txt)
- Dream-in-4D: A Unified Approach for Text- and Image-guided 4D Scene Generation - in-4d.txt)
- Align Your Gaussians:Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models
- Ponymation: Learning 3D Animal Motions from Unlabeled Online Videos
- DreamGaussian4D: Generative 4D Gaussian Splatting - ren/dreamgaussian4d) | [bibtext](./citations/dreamgaussian4d.txt)
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
- 3D Gaussian Splatting for Real-Time Radiance Field Rendering - inria/gaussian-splatting) | [bibtex](./citations/3dgaussian.txt)
- Uni3D: Exploring Unified 3D Representation at Scale
- SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene
- GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images - tlabs/GET3D) | [bibtex](./citations/get3d.txt)
- LION: Latent Point Diffusion Models for 3D Shape Generation - tlabs/LION) | [bibtex](./citations/lion.txt)
- Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions - computational-imaging/Diffusion-SDF) | [bibtex](./citations/diffusionsdf.txt)
- DiffRF: Rendering-guided 3D Radiance Field Diffusion
- Point-E: A System for Generating 3D Point Clouds from Complex Prompts - e) | [bibtex](./citations/pointe.txt)
- MeshDiffusion: Score-based Generative 3D Mesh Modeling
- 3DGen: Triplane Latent Diffusion for Textured Mesh Generation
- HoloDiffusion: Training a 3D Diffusion Model using 2D Images
- HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion
- Shap-E: Generating Conditional 3D Implicit Functions - e) | [bibtex](./citations/shape.txt)
- LAS-Diffusion: Locally Attentional SDF Diffusion for Controllable 3D Shape Generation - Diffusion) | [bibtex](./citations/lasdiffusion.txt)
- ARGUS: Visualization of AI-Assisted Task Guidance in AR
- WildFusion:Learning 3D-Aware Latent Diffusion Models in View Space
- X3: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies
- MagicPony: Learning Articulated 3D Animals in the Wild
- Learning the 3D Fauna of the Web
- CityDreamer: Compositional Generative Model of Unbounded 3D Cities - dreamer) | [bibtext](./citations/cityDreamer.txt)
- Generating Parametric BRDFs from Natural Language Descriptions
- MATLABER: Material-Aware Text-to-3D via LAtent BRDF auto-EncodeR
- CLIP-Mesh: Generating textured meshes from text using pretrained image-text models - Mesh) | [bibtex](./citations/clipmesh.txt)
- Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures - nerf) | [bibtex](./citations/latentNerf.txt)
- TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models
- MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion
- RoomDreamer: Text-Driven 3D Indoor Scene Synthesis with Coherent Geometry and Texture
- 3DStyle-Diffusion: Pursuing Fine-grained Text-driven 3D Stylization with 2D Diffusion Models - fdu/3DStyle-Diffusion-Official) | [bibtex](./citations/3dstylediffusion.txt)
- DreamSpace: Dreaming Your Room Space with Text-Driven Panoramic Texture Propagation
- Text-Guided Texturing by Synchronized Multi-View Diffusion
- TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes
- Single Mesh Diffusion Models with Field Latents for Texture Generation
- Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering - ami/paint-it) | [bibtext](./citations/paint-it.txt)
- Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models
- LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models - tlabs/LLaMa-Mesh) | [bibtext](./citations/LLaMa-Mesh.txt)
- Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle - YuanGroup/Cycle3D) | [bibtext](./citations/cycle3d.txt)
- BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometry
- Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer
- Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models - Group/Diffusion4D) | [bibtext](./citations/diffusion4d.txt)
- Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels
- Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
- Fourier123: One Image to High-Quality 3D Object Generation with Hybrid Fourier Score Distillation
- Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion
- IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation - Kyriazi et al., arxiv 2024 | [bibtex](./citations/im3d.txt)
- TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion
- Consistent3D: Towards Consistent High-Fidelity Text-to-3D Generation with Deterministic Sampling Prior
- FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding - ->
- Fast Dynamic 3D Object Generation from a Single-view Video - zvg/Efficient4D) | [bibtext](./citations/efficient4d.txt)
- Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis
- MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization
- SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement - AI/stable-fast-3d) | [bibtex](./citations/sf3d.txt)
- ScaleDreamer: Scalable Text-to-3D Synthesis with Asynchronous Score Distillation
- GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation
- Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D
- Sketch3D: Style-Consistent Guidance for Sketch-to-3D Generation
- InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
- Diffusion^2: Dynamic 3D Content Generation via Score Composition of Orthogonal Diffusion Models
- Physical Property Understanding from Language-Embedded Feature Fields
- ATISS: Autoregressive Transformers for Indoor Scene Synthesis - tlabs/atiss) | [bibtext](./citations/atiss.txt)
- DiffuScene: Scene Graph Denoising Diffusion Probabilistic Model for Generative Indoor Scene Synthesis
- MeshAnything:Artist-Created Mesh Generation with Autoregressive Transformers
- 4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models
- CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model - ml/CRM) | [bibtext](./citations/crm.txt)
- L4GM: Large 4D Gaussian Reconstruction Model
- 3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion - XL) | [bibtex](./citations/3dtopia-xl.txt)
- EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation
- ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis
- ICE-G: Image Conditional Editing of 3D Gaussian Splats
- VQA-Diff: Exploiting VQA and Diffusion for Zero-Shot Image-to-3D Vehicle Asset Generation in Autonomous Driving
- Physically Compatible 3D Object Modeling from a Single Image
- LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation
- SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion
- DreamReward: Text-to-3D Generation with Human Preference
- SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency - AI/generative-models) | [bibtext](./citations/stablev3d.txt)
- MeshXL: Neural Coordinate Field for Generative 3D Foundation Models
- G3PT: Unleash the power of Autoregressive Modeling in 3D Generation via Cross-scale Querying Transformer
- Retrieval-Augmented Score Distillation for Text-to-3D Generation - CVLAB/RetDream) | [bibtex](./citations/retdream.txt)
- LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation
- EscherNet: A Generative Model for Scalable View Synthesis
- Make-it-Real: Unleashing Large Multimodal Model's Ability for Painting 3D Objects with Realistic Materials - it-real.txt)
- Slice3D: Multi-Slice, Occlusion-Revealing, Single View 3D Reconstruction
- DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing - chen/DGE) | [bibtex](./citations/dge.txt)
- MicroDreamer: Zero-shot 3D Generation in ∼20 Seconds by Score-based Iterative Reconstruction - GSAI/MicroDreamer) | [bibtex](./citations/microdreamer.txt)
- DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
- MaPa: Text-driven Photorealistic Material Painting for 3D Shapes
- GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
- DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
- DiffComplete: Diffusion-based Generative 3D Shape Completion
- DUSt3R: Geometric 3D Vision Made Easy
- Disentangled 3D Scene Generation with Layout Learning
- ViewFusion: Towards Multi-View Consistency via Interpolated Denoising - sc/ViewFusion) | [bibtex](./citations/viewfusion.txt)
- Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation - Lab-SCUT/Fantasia3D) | [bibtex](./citations/fantasia3d.txt)
- Single-View 3D Human Digitalization with Large Reconstruction Models
- Pyramid Diffusion for Fine 3D Large Scene Generation - page/pyramid-discrete-diffusion/) | [bibtext](./citations/pyramid.txt)
- XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies
- SMPLicit: Topology-aware Generative Model for Clothed People
- HeadNeRF: A Real-time NeRF-based Parametric Head Model
- gDNA: Towards Generative Detailed Neural Avatars - ethz/gdna) | [bibtext](./citations/gdna.txt)
- DreamFields: Zero-Shot Text-Guided Object Generation with Dream Fields - research/google-research/tree/master/dreamfields) | [bibtex](./citations/dreamfields.txt)
- DreamFusion: Text-to-3D using 2D Diffusion - dreamfusion) | [bibtex](./citations/dreamfusion.txt)
- Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models
- Magic3D: High-Resolution Text-to-3D Content Creation
- Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation - ttic/sjc/)| [bibtex](./citations/sjc.txt)
- 3DFuse: Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation - CVLAB/3DFuse) | [bibtex](./citations/3dfuse.txt)
- DreamBooth3D: Subject-Driven Text-to-3D Generation
- Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior - It-3D) | [bibtex](./citations/makeit3d.txt)
- HiFA: High-fidelity Text-to-3D with Advanced Diffusion Guidance - team/HiFA) | [bibtex](./citations/hifa.txt)
- ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation - ml/prolificdreamer) | [bibtex](./citations/prolificdreamer.txt)
- NFSD: Noise Free Score Distillation
- Text-to-3D with Classifier Score Distillation - Lab/Classifier-Score-Distillation) | [bibtex](./citations/csd.txt)
- Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts
- Instant3D : Instant Text-to-3D Generation
- CG3D: Compositional Generation for Text-to-3D via Gaussian Splatting
- CAD: Photorealistic 3D Generation via Adversarial Distillation
- AGAP:Learning Naturally Aggregated Appearance for Efficient 3D Editing
- SteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identity - Group/SteinDreamer) | [bibtex](./citations/steindreamer.txt)
- Taming Mode Collapse in Score Distillation for Text-to-3D Generation - Group/3D-Mode-Collapse) | [bibtex](./citations/3d-mode-collapse.txt)
- Text2Light: Zero-Shot Text-Driven HDR Panorama Generation
- SceneScape: Text-Driven Consistent Scene Generation
- Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models
- Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields
- GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting
- LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes - cvlab/LucidDreamer) | [bibtext](./citations/luciddreamer-scene.txt)
- SceneWiz3D: Towards Text-guided 3D Scene Composition
- ShowRoom3D: Text to High-Quality 3D Room Generation Using 3D Priors
- GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting
- SofGAN: A Portrait Image Generator with Dynamic Styling
- Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model using Pixel-aligned Reconstruction Priors - zhangyang/Get3DHuman) | [bibtext](./citations/get3dhuman.txt)
- DreamFace: Progressive Generation of Animatable 3D Faces under Text Guidance
- TADA! Text to Animatable Digital Avatars
- SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes
- HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation
- MAV3d: Text-To-4D Dynamic Scene Generation
- Control4D: Dynamic Portrait Editing by Learning 4D GAN from 2D Diffusion-based Editor
- MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusion
- Consistent4D: Consistent 360° Dynamic Object Generation from Monocular Video
- Animate124: Animating One Image to 4D Dynamic Scene
- A Unified Approach for Text- and Image-guided 4D Scene Generation - in-4d.txt)
- 4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling
- Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings
- ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model
- GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images - tlabs/GET3D) | [bibtex](./citations/get3d.txt)
- LION: Latent Point Diffusion Models for 3D Shape Generation - tlabs/LION) | [bibtex](./citations/lion.txt)
- Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions - computational-imaging/Diffusion-SDF) | [bibtex](./citations/diffusionsdf.txt)
- MagicPony: Learning Articulated 3D Animals in the Wild
- DiffRF: Rendering-guided 3D Radiance Field Diffusion
- SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation
- 3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models
- MeshDiffusion: Score-based Generative 3D Mesh Modeling
- HoloDiffusion: Training a 3D Diffusion Model using 2D Images
- HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion
- LAS-Diffusion: Locally Attentional SDF Diffusion for Controllable 3D Shape Generation - Diffusion) | [bibtex](./citations/lasdiffusion.txt)
- Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation
- DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation - 3D/DiT-3D) | [bibtext](./citations/dit3d.txt)
- 3D VADER - AutoDecoding Latent 3D Diffusion Models - research/3DVADER) | [bibtex](./citations/3dvader.txt)
- Large-Vocabulary 3D Diffusion Model with Transformer
- TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields
- HyperFields:Towards Zero-Shot Generation of NeRFs from Text
- LRM: Large Reconstruction Model for Single Image to 3D
- DMV3D:Denoising Multi-View Diffusion using 3D Large Reconstruction Model
- WildFusion:Learning 3D-Aware Latent Diffusion Models in View Space
- MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers - gpt) | [bibtex](./citations/meshgpt.txt)
- ZeroRF: Fast Sparse View 360° Reconstruction with Zero Pretraining
- Learning the 3D Fauna of the Web
- Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability - 3D) | [bibtext](./citations/argus3d.txt)
- GAUDI: A Neural Architect for Immersive 3D Scene Generation - gaudi) | [bibtext](./citations/gaudi.txt)
- NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models
- GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions
- Inpaint3D: 3D Scene Content Generation using 2D Inpainting Diffusion
- SIGNeRF: Scene Integrated Generation for Neural Radiance Fields
- AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars
- DreamWaltz: Make a Scene with Complex 3D Animatable Avatars - Research/DreamWaltz) | [bibtex](./citations/dreamwaltz.txt)
- DreamHuman: Animatable 3D Avatars from Text
- TECA: Text-Guided Generation and Editing of Compositional 3D Avatars
- HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
- HeadArtist: Text-conditioned 3D Head Generation with Self Score Distillation
- Zero-1-to-3: Zero-shot One Image to 3D Object - columbia/zero123) | [bibtex](./citations/zero123.txt)
- One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization - 2-3-45/One-2-3-45) | [bibtex](./citations/one2345.txt)
- Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
- MVDream: Multi-view Diffusion for 3D Generation
- SyncDreamer: Generating Multiview-consistent Images from a Single-view Image - pal.github.io/SyncDreamer/) | [bibtex](./citations/syncdreamer.txt)
- Gsgen: Text-to-3D using Gaussian Splatting
- GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models
- Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models
- TOSS: High-quality Text-guided Novel View Synthesis from a Single Image
- Wonder3D: Single Image to 3D using Cross-Domain Diffusion
- DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior - ai/DreamCraft3D) | [bibtex](./citations/dreamcraft3d.txt)
- SweetDreamer: Aligning Geometric Priors in 2D Diffusion for Consistent Text-to-3D - 98/SweetDreamer) | [bibtex](./citations/sweetdreamer.txt)
- One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion - AI-3D/One2345plus) | [bibtex](./citations/one2345++.txt)
- Direct2.5: Diverse Text-to-3D Generation via Multi-view 2.5D Diffusion
- Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model
- MVControl: Adding Conditional Control to Multi-view Diffusion for Controllable Text-to-3D Generation - CVGL/MVControl/) | [bibtex](./citations/mvcontorl.txt)
- GeoDream:Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation
- RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D
- DreamComposer: Controllable 3D Object Generation via Multi-View Conditions - myron/DreamComposer) | [bibtex](./citations/dreamcomposer.txt)
- Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Views - Zero123) | [bibtex](./citations/cascadeZero123.txt)
- Free3D: Consistent Novel View Synthesis without 3D Representation
- UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generation
- Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting
- BiDiff: Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors
- ControlDreamer: Stylized 3D Generation with Multi-View ControlNet
- X-Dreamer: Creating High-quality 3D Content by Bridging the Domain Gap Between Text-to-2D and Text-to-3D Generation - xiaoma666/X-Dreamer) | [bibtex](./citations/xdreamer.txt)
- Splatter Image: Ultra-Fast Single-View 3D Reconstruction - image) | [bibtex](./citations/splatter-image.txt)
- Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning
- HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D - park/HarmonyView) | [bibtex](./citations/harmonyView.txt)
- ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation
- iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse Views
- MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction
- MVD2: Efficient Multiview 3D Reconstruction for Multiview Diffusion
- Consolidating Attention Features for Multi-view Image Editing
- Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints - Room) | [bibtext](./citations/ctrlroom.txt)
- ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Real Image
- GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs
- ControlRoom3D:Room Generation using Semantic Proxy Rooms
- AnimatableDreamer: Text-Guided Non-rigid 3D Model Generation and Reconstruction with Canonical Score Distillation - dreamer.txt)
- Virtual Pets: Animatable Animal Generation in 3D Scenes - pets.txt)
- Align Your Gaussians:Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models
- Ponymation: Learning 3D Animal Motions from Unlabeled Online Videos
- 4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency - Group/4DGen) | [bibtext](./citations/4dgen.txt)
- DreamGaussian4D: Generative 4D Gaussian Splatting - ren/dreamgaussian4d) | [bibtext](./citations/dreamgaussian4d.txt)
- StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions
- CLIP-Mesh: Generating textured meshes from text using pretrained image-text models - Mesh) | [bibtex](./citations/clipmesh.txt)
- TANGO: Text-driven PhotoreAlistic aNd Robust 3D Stylization via LiGhting DecompOsition - Lab-SCUT/tango) | [bibtex](./citations/tango.txt)
- TEXTure: Text-Guided Texturing of 3D Shapes
- Text2Tex: Text-driven Texture Synthesis via Diffusion Models
- MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion
- MATLABER: Material-Aware Text-to-3D via LAtent BRDF auto-EncodeR
- ITEM3D: Illumination-Aware Directional Texture Editing for 3D Models
- TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models
- DreamSpace: Dreaming Your Room Space with Text-Driven Panoramic Texture Propagation
- SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors
- Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering - ami/paint-it) | [bibtext](./citations/paint-it.txt)
- FlashTex: Fast Relightable Mesh Texturing with LightControlNet
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
- 3D Gaussian Splatting for Real-Time Radiance Field Rendering - inria/gaussian-splatting) | [bibtex](./citations/3dgaussian.txt)
- SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene
- Triplane Meets Gaussian Splatting:Fast and Generalizable Single-View 3D Reconstruction with Transformers
- SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes - GS) | [bibtex](./citations/scgs.txt)
- Functional Diffusion - diffusion) | [bibtex](./citations/fd.txt)
- Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior
- Make-Your-3D: Fast and Consistent Subject-Driven 3D Content Generation - Your-3D) | [bibtext](./citations/make_your_3d.txt)
- Controllable Text-to-3D Generation via Surface-Aligned Gaussian Splatting - CVGL/MVControl/) | [bibtex](./citations/controllable.txt)
- VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model
- DreamView: Injecting View-specific Text Guidance into Text-to-3D Generation - Laboratory/DreamView) | [bibtex](./citations/dreamview.txt)
- ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance
- Hash3D: Training-free Acceleration for 3D Generation
- SPiC·E: Structural Priors in 3D Diffusion Models using Cross-Entity Attention - VAILab/spic-e) | [bibtex](./citations/spice.txt)
- RealFusion: 360° Reconstruction of Any Object from a Single Image - Kyriazi et al., CVPR 2023 | [github](https://github.com/lukemelas/realfusion) | [bibtex](./citations/realfusion.txt)
- Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion - Diffusion) | [bibtext](./citations/Phidias.txt)
- STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians
- ThemeStation: Generating Theme-Aware 3D Assets from Few Exemplars
- MeshLRM: Large Reconstruction Model for High-Quality Meshes
- Magic-Boost: Boost 3D Generation with Mutli-View Conditioned Diffusion - research/magic-boost) | [bibtext](./citations/magicboost.txt)
- Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondences - view-correspondences.txt)
- DMesh: A Differentiable Representation for General Meshes
- FlexiDreamer: Single Image-to-3D Generation with FlexiCubes
- TC4D: Trajectory-Conditioned Text-to-4D Generation
- Interactive3D🪄: Create What You Want by Interactive 3D Generation - 3d/interactive3d) | [bibtex](./citations/interactive3D.txt)
- CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets - 3D/OpenCLAY) | [bibtex](./citations/clay.txt)
- GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Quality
- Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materials
- Meta 3D TextureGen: Fast and Consistent Texture Generation for 3D Objects
- CraftsMan: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner - 98/CraftsMan) | [bibtext](./citations/craftsman.txt)
- Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image
- SMPL: A skinned multi-person linear model
- Efficient Large-Baseline Radiance Fields, a feed-forward 2DGS model
-
Survey
- Generative AI meets 3D: A Survey on Text-to-3D in AIGC Era
- 3D Generative Models: A Survey - generative-survey.txt)
- Geometric Constraints in Deep Learning Frameworks: A Survey
- AI-Generated Content (AIGC) for Various Data Modalities: A Survey
- Advances in 3D Generation: A Survey - 3dgeneration.txt)
- A Comprehensive Survey on 3D Content Generation
- Advances in 3D Generation: A Survey - 3dgeneration.txt)
-
Benchmarks and Datasets
- Objaverse-XL - xl) | [bibtext](./citations/objaverse-xl.txt)
- GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation
- G-buffer Objaverse: High-Quality Rendering Dataset of Objaverse
- SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding
- Make-A-Shape: a Ten-Million-scale 3D Shape Model - a-shape.txt)
- Zeroverse
-
Talks
-
Implementations
- Threestudio - Chen Guo, 2023 | [bibtex](./citations/threestudio.txt)
- stable-dreamfusion - dreamfusion.txt)
- Dream Textures
- ComfyTextures
- ComfyUI-3D-Pack
- GauStudio - LAB-CUHK-SZ/gaustudio) | [bibtex](./citations/gaustudio.txt)
-
Company
Programming Languages
Sub Categories