SOTAVerified

3D geometry

Papers

Showing 150 of 684 papers

TitleStatusHype
Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse AttentionCode5
Wonder3D: Single Image to 3D using Cross-Domain DiffusionCode5
GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single ImageCode4
CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry RefinerCode4
You See it, You Got it: Learning 3D Creation on Pose-Free Videos at ScaleCode4
GeoCalib: Learning Single-image Calibration with Geometric OptimizationCode4
CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D AssetsCode4
NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image PriorsCode4
Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image ModelsCode3
TAPIP3D: Tracking Any Point in Persistent 3D GeometryCode3
Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion PriorCode3
ShapeLLM: Universal 3D Object Understanding for Embodied InteractionCode3
MagicDrive: Street View Generation with Diverse 3D Geometry ControlCode3
Towards Realistic Scene Generation with LiDAR Diffusion ModelsCode3
TripNet: Learning Large-scale High-fidelity 3D Car Aerodynamics with Triplane NetworksCode3
VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene CompletionCode3
AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D AvatarsCode3
DFormerv2: Geometry Self-Attention for RGBD Semantic SegmentationCode3
3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D GenerationCode3
LiftFeat: 3D Geometry-Aware Local Feature MatchingCode3
ThermoNeRF: Joint RGB and Thermal Novel View Synthesis for Building Facades using Multimodal Neural Radiance FieldsCode2
Tex4D: Zero-shot 4D Scene Texturing with Video Diffusion ModelsCode2
Total-Decom: Decomposed 3D Scene Reconstruction with Minimal InteractionCode2
DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video GenerationCode2
Recollection from Pensieve: Novel View Synthesis via Learning from Uncalibrated VideosCode2
ConceptFusion: Open-set Multimodal 3D MappingCode2
Distilled Feature Fields Enable Few-Shot Language-Guided ManipulationCode2
Tetra-NeRF: Representing Neural Radiance Fields Using TetrahedraCode2
Deep Height Decoupling for Precise Vision-based 3D Occupancy PredictionCode2
Retrieval-Augmented Score Distillation for Text-to-3D GenerationCode2
Single-View View Synthesis in the Wild with Learned Adaptive Multiplane ImagesCode2
DFormer: Rethinking RGBD Representation Learning for Semantic SegmentationCode2
Model-Based Imitation Learning for Urban DrivingCode2
NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object DetectionCode2
L-PR: Exploiting LiDAR Fiducial Marker for Unordered Low Overlap Multiview Point Cloud RegistrationCode2
gRNAde: Geometric Deep Learning for 3D RNA inverse designCode2
Learning Physically Realizable Skills for Online Packing of General 3D ShapesCode2
Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous DrivingCode2
GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual LocalizationCode2
Depth-Aware Generative Adversarial Network for Talking Head Video GenerationCode2
HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion GuidanceCode2
GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action ControlCode2
iHuman: Instant Animatable Digital Humans From Monocular VideosCode2
Any2Point: Empowering Any-modality Large Models for Efficient 3D UnderstandingCode2
End-to-End Vectorized HD-map Construction with Piecewise Bezier CurveCode2
MonoOcc: Digging into Monocular Semantic Occupancy PredictionCode2
Feed-Forward SceneDINO for Unsupervised Semantic Scene CompletionCode2
Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language NavigationCode2
Efficient Geometry-aware 3D Generative Adversarial NetworksCode2
EMOCA: Emotion Driven Monocular Face Capture and AnimationCode2
Show:102550
← PrevPage 1 of 14Next →

No leaderboard results yet.