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 76–100 of 314 papers

TitleStatusHype
Towards Rich Emotions in 3D Avatars: A Text-to-3D Avatar Generation BenchmarkCode1
DreamView: Injecting View-specific Text Guidance into Text-to-3D GenerationCode1
RewardSDS: Aligning Score Distillation via Reward-Weighted SamplingCode1
Connecting Consistency Distillation to Score Distillation for Text-to-3D GenerationCode1
DreamPropeller: Supercharge Text-to-3D Generation with Parallel SamplingCode1
Progressive Text-to-3D Generation for Automatic 3D PrototypingCode1
ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score DistillationCode1
Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-trainingCode1
Magic3D: High-Resolution Text-to-3D Content CreationCode1
Set-the-Scene: Global-Local Training for Generating Controllable NeRF ScenesCode1
IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image PromptsCode1
Intelligent Home 3D: Automatic 3D-House Design from Linguistic Descriptions OnlyCode1
Instant3D: Instant Text-to-3D GenerationCode1
High-Fidelity 3D Face Generation from Natural Language DescriptionsCode1
Cephalo: Multi-Modal Vision-Language Models for Bio-Inspired Materials Analysis and DesignCode1
DreamControl: Control-Based Text-to-3D Generation with 3D Self-PriorCode1
Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset UpdatesCode1
Fast Text-to-3D-Aware Face Generation and Manipulation via Direct Cross-modal Mapping and Geometric RegularizationCode1
A General Framework to Boost 3D GS Initialization for Text-to-3D Generation by Lexical RichnessCode1
Sherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D PriorCode1
DirectTriGS: Triplane-based Gaussian Splatting Field Representation for 3D Generation—0
Direct2.5: Diverse Text-to-3D Generation via Multi-view 2.5D Diffusion—0
BoostDream: Efficient Refining for High-Quality Text-to-3D Generation from Multi-View Diffusion—0
DepthLab: From Partial to Complete—0
Benchmarking and Learning Multi-Dimensional Quality Evaluator for Text-to-3D Generation—0
Show:102550
← PrevPage 4 of 13Next →

Benchmark Results

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