SOTAVerified

Text to 3D

Task involves generating 3D objects based on the text prompt provided to the system.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 314 papers

TitleStatusHype
DreamFusion: Text-to-3D using 2D DiffusionCode5
Text-to-Image Rectified Flow as Plug-and-Play PriorsCode5
Generating Physically Stable and Buildable LEGO Designs from TextCode5
Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and BeyondCode5
ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View SynthesisCode5
GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and GenerationCode4
3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion PriorsCode4
Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset GenerationCode3
BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvementCode3
Director3D: Real-world Camera Trajectory and 3D Scene Generation from TextCode3
Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text PromptsCode3
PuzzleAvatar: Assembling 3D Avatars from Personal AlbumsCode3
Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion PriorCode3
Generic 3D Diffusion Adapter Using Controlled Multi-View EditingCode3
3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D GenerationCode3
SceneCraft: Layout-Guided 3D Scene GenerationCode3
ViewDiff: 3D-Consistent Image Generation with Text-to-Image ModelsCode3
View Selection for 3D Captioning via Diffusion RankingCode3
Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image ModelsCode3
One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape OptimizationCode3
Controllable Text-to-3D Generation via Surface-Aligned Gaussian SplattingCode3
T^3Bench: Benchmarking Current Progress in Text-to-3D GenerationCode3
GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D GenerationCode3
Scalable 3D Captioning with Pretrained ModelsCode2
IT3D: Improved Text-to-3D Generation with Explicit View SynthesisCode2
Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D GenerationCode2
ScaleDreamer: Scalable Text-to-3D Synthesis with Asynchronous Score DistillationCode2
InterFusion: Text-Driven Generation of 3D Human-Object InteractionCode2
LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score MatchingCode2
Latent-NeRF for Shape-Guided Generation of 3D Shapes and TexturesCode2
Hyper-3DG: Text-to-3D Gaussian Generation via HypergraphCode2
Isotropic3D: Image-to-3D Generation Based on a Single CLIP EmbeddingCode2
Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D DataCode2
Retrieval-Augmented Score Distillation for Text-to-3D GenerationCode2
GradeADreamer: Enhanced Text-to-3D Generation Using Gaussian Splatting and Multi-View DiffusionCode2
GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D GenerationCode2
PERF: Panoramic Neural Radiance Field from a Single PanoramaCode2
GarmentDreamer: 3DGS Guided Garment Synthesis with Diverse Geometry and Texture DetailsCode2
Generate Any Scene: Evaluating and Improving Text-to-Vision Generation with Scene Graph ProgrammingCode2
Efficient4D: Fast Dynamic 3D Object Generation from a Single-view VideoCode2
Hash3D: Training-free Acceleration for 3D GenerationCode2
GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion ModelsCode2
PlacidDreamer: Advancing Harmony in Text-to-3D GenerationCode2
MVControl: Adding Conditional Control to Multi-view Diffusion for Controllable Text-to-3D GenerationCode2
Dreamer XL: Towards High-Resolution Text-to-3D Generation via Trajectory Score MatchingCode2
Consistent3D: Towards Consistent High-Fidelity Text-to-3D Generation with Deterministic Sampling PriorCode2
Apply Hierarchical-Chain-of-Generation to Complex Attributes Text-to-3D GenerationCode2
DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D DiffusionCode2
Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction ModelCode2
NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360° ViewsCode2
Show:102550
← PrevPage 1 of 7Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ProlificDreamerAvg43.3—Unverified
2Magic3DAvg32.7—Unverified
3LatentNeRFAvg28.1—Unverified
4Fantasia3DAvg24—Unverified
5DreamFusionAvg21.7—Unverified
6SJCAvg18.7—Unverified