worldbench / awesome-3d-4d-world-modelsLinks
🌐 3D and 4D World Modeling: A Survey
☆742Updated last week
Alternatives and similar repositories for awesome-3d-4d-world-models
Users that are interested in awesome-3d-4d-world-models are comparing it to the libraries listed below
Sorting:
- G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning☆226Updated 3 weeks ago
- This is the repository that contains source code for the PhysGen3D.☆236Updated 3 months ago
- [NeurIPS'25] Official repository of Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations☆454Updated 3 weeks ago
- Official implementation of "Next-Scale Autoregressive Models are Zero-Shot Single-Image Object View Synthesizers"☆46Updated 9 months ago
- [CVPR 2025, All Strong Accept] TSP3D: Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding☆244Updated 6 months ago
- [ICCV 2025] DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation☆173Updated 4 months ago
- ☆140Updated 9 months ago
- [CORL 2025 Oral]One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation.☆431Updated 4 months ago
- Official implementation of "DepthLab: From Partial to Complete"☆535Updated 10 months ago
- SAM 3D Objects with Multi-view Images☆143Updated 2 weeks ago
- [CVPR 2025] UniScene: Unified Occupancy-centric Driving Scene Generation☆536Updated last month
- The Most Faithful Implementation of Segment Anything (SAM) in 3D☆352Updated last year
- A Unified Driving World Model for Future Generation and Perception☆128Updated 5 months ago
- [NeurIPS 2025] Official code of Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting☆135Updated 3 weeks ago
- [ICLR 2025, Oral] EmbodiedSAM: Online Segment Any 3D Thing in Real Time☆603Updated 7 months ago
- The implementation of SUNDAE: Spectrally Pruned Gaussian Fields with Neural Compensation☆164Updated last year
- ICCV 2025 | TesserAct: Learning 4D Embodied World Models☆367Updated 4 months ago
- ☆687Updated 7 months ago
- [NeurIPS 2025 DB Track] 3EED: Ground Everything Everywhere in 3D☆195Updated 2 weeks ago
- Official implementation for paper: InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior☆546Updated last year
- [T-PAMI 2025] SceneTracker: Long-term Scene Flow Estimation Network☆129Updated 6 months ago
- [SIGGRAPH 2025] Officially implement of the paper "Drag Your Gaussian: Effective Drag-Based Editing with Score Distillation for 3D Gaussi…☆152Updated 8 months ago
- A curated list of awesome papers for reconstructing 4D spatial intelligence from video. (arXiv 2507.21045)☆397Updated 2 weeks ago
- VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction☆310Updated 3 months ago
- Official implementation for SlimmeRF: Slimmable Radiance Fields (3DV 2024 Best Paper)☆146Updated last year
- [ICLR 2025 Spotlight] Official implementation for "DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes"☆228Updated 4 months ago
- OmniNWM: Omniscient Navigation World Models for Autonomous Driving☆263Updated last month
- [ACMMM 2025] Officially implement of the paper "DriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompti…☆211Updated 7 months ago
- [ICRA 2025] PUGS: Zero-shot Physical Understanding with Gaussian Splatting.☆102Updated 9 months ago
- ☆276Updated last month