SOTAVerified

Scene Generation

make to t shirt an Ad with a little bit of action

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–125 of 309 papers

TitleStatusHype
PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Scenes—0
DreamCube: 3D Panorama Generation via Multi-plane Synchronization—0
4Real-Video-V2: Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation—0
ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies—0
X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability—0
EmbodiedGen: Towards a Generative 3D World Engine for Embodied Intelligence—0
NnD: Diffusion-based Generation of Physically-Nonnegative Objects—0
Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency—0
PIG: Physically-based Multi-Material Interaction with 3D Gaussians—0
AI-powered Contextual 3D Environment Generation: A Systematic Review—0
Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation—0
FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts—0
ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary—0
Automatic Scene Generation: State-of-the-Art Techniques, Models, Datasets, Challenges, and Future Prospects—0
Agentic 3D Scene Generation with Spatially Contextualized VLMs—0
WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions—0
Constructing a 3D Town from a Single Image—0
MCCD: Multi-Agent Collaboration-based Compositional Diffusion for Complex Text-to-Image Generation—0
Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation—0
CasaGPT: Cuboid Arrangement and Scene Assembly for Interior Design—0
Recent Advance in 3D Object and Scene Generation: A Survey—0
WORLDMEM: Long-term Consistent World Simulation with Memory—0
GaussVideoDreamer: 3D Scene Generation with Video Diffusion and Inconsistency-Aware Gaussian Splatting—0
Decoupled Diffusion Sparks Adaptive Scene Generation—0
EP-Diffuser: An Efficient Diffusion Model for Traffic Scene Generation and Prediction via Polynomial RepresentationsCode0
Show:102550
← PrevPage 5 of 13Next →
All datasetsGoogleEarthAVDReplicaVizDoomOSMKITTI

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SGAMDepth Error0.58—Unverified
2PersistentNatureDepth Error0.33—Unverified
3SceneDreamerDepth Error0.15—Unverified
4CityDreamerDepth Error0.15—Unverified
5GaussianCityDepth Error0.14—Unverified
#ModelMetricClaimedVerifiedStatus
1pi-GANFID98.76—Unverified
2GRAFFID62.59—Unverified
3GSNFID51.11—Unverified
#ModelMetricClaimedVerifiedStatus
1pi-GANFID166.55—Unverified
2GRAFFID65.37—Unverified
3GSNFID41.75—Unverified
#ModelMetricClaimedVerifiedStatus
1pi-GANFID143.55—Unverified
2GRAFFID47.5—Unverified
3GSNFID37.21—Unverified
#ModelMetricClaimedVerifiedStatus
1IPSMAverage FID321.47—Unverified
2InfiniteGANAverage FID183.14—Unverified
#ModelMetricClaimedVerifiedStatus
1GaussianCityFID29.5—Unverified