SOTAVerified

Scene Generation

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 309 papers

TitleStatusHype
SG-Tailor: Inter-Object Commonsense Relationship Reasoning for Scene Graph ManipulationCode0
Decorum: A Language-Based Approach For Style-Conditioned Synthesis of Indoor 3D Scenes—0
HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generation—0
NuiScene: Exploring Efficient Generation of Unbounded Outdoor ScenesCode2
DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation—0
Cube: A Roblox View of 3D IntelligenceCode4
SceneEval: Evaluating Semantic Coherence in Text-Conditioned 3D Indoor Scene Synthesis—0
Advances in 4D Generation: A SurveyCode2
ChatBEV: A Visual Language Model that Understands BEV Maps—0
SimWorld: A Unified Benchmark for Simulator-Conditioned Scene Generation via World ModelCode1
Bolt3D: Generating 3D Scenes in Seconds—0
Seeing the Future, Perceiving the Future: A Unified Driving World Model for Future Generation and PerceptionCode2
SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric SteeringCode2
WonderVerse: Extendable 3D Scene Generation with Video Generative Models—0
Controllable 3D Outdoor Scene Generation via Scene GraphsCode2
Unlocking Generalization for Robotics via Modularity and Scale—0
DualDiff+: Dual-Branch Diffusion for High-Fidelity Video Generation with Reward GuidanceCode1
Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized DetectionCode1
A Survey on Text-Driven 360-Degree Panorama Generation—0
Rolling Ahead Diffusion for Traffic Scene Simulation—0
MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene GenerationCode1
Functional 3D Scene Synthesis through Human-Scene Optimization—0
LAYOUTDREAMER: Physics-guided Layout for Text-to-3D Compositional Scene Generation—0
PhiP-G: Physics-Guided Text-to-3D Compositional Scene Generation—0
HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and GenerationCode3
BloomScene: Lightweight Structured 3D Gaussian Splatting for Crossmodal Scene GenerationCode0
CityDreamer4D: Compositional Generative Model of Unbounded 4D CitiesCode2
StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene Generation—0
Layout2Scene: 3D Semantic Layout Guided Scene Generation via Geometry and Appearance Diffusion Priors—0
MRG: A Multi-Robot Manufacturing Digital Scene Generation Method Using Multi-Instance Point Cloud Registration—0
FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement—0
Robust Multi-Object 4D Generation for In-the-wild Videos—0
SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Model—0
DreamDrive: Generative 4D Scene Modeling from Street View Images—0
Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation—0
Toward Scene Graph and Layout Guided Complex 3D Scene Generation—0
DepthLab: From Partial to Complete—0
OLiDM: Object-aware LiDAR Diffusion Models for Autonomous Driving—0
T^3-S2S: Training-free Triplet Tuning for Sketch to Scene GenerationCode0
Wonderland: Navigating 3D Scenes from a Single Image—0
OccScene: Semantic Occupancy-based Cross-task Mutual Learning for 3D Scene Generation—0
GPD-1: Generative Pre-training for DrivingCode2
LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural AnnotationsCode2
UniScene: Unified Occupancy-centric Driving Scene GenerationCode4
SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rollout—0
PaintScene4D: Consistent 4D Scene Generation from Text Prompts—0
InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models—0
Supertoroid fitting of objects with holes for robotic grasping and scene generationCode0
SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation—0
HoloDrive: Holistic 2D-3D Multi-Modal Street Scene Generation for Autonomous Driving—0
Show:102550
← PrevPage 2 of 7Next →
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