zju3dv / EgoAgentLinks
Official implementation of ICCV 2025 paper "EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds".
☆41Updated 5 months ago
Alternatives and similar repositories for EgoAgent
Users that are interested in EgoAgent are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] Where Am I and What Will I See : An Auto-Regressive Model for Spatial Localization and View Prediction☆42Updated 4 months ago
- [NeurIPS 25] TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels☆51Updated this week
- DELTA: Dense Efficient Long-range 3D Tracking for Any video (ICLR 2025)☆135Updated 8 months ago
- UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding☆56Updated 3 months ago
- Code for "BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation", ICCV 2025.☆97Updated 2 months ago
- [NeurIPS 2025] PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation☆88Updated last week
- [NeurIPS 2025] InternScenes: A Large-scale Interactive Indoor Scene Dataset with Realistic Layouts.☆200Updated last month
- ☆102Updated 2 months ago
- Official Implementation of paper "St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World"☆93Updated 2 months ago
- ☆38Updated 8 months ago
- ☆32Updated last year
- Official Reporsitory of "EgoMono4D: Self-Supervised Monocular 4D Scene Reconstruction for Egocentric Videos"☆39Updated 2 months ago
- UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation☆134Updated 6 months ago
- Seeing World Dynamics in a Nutshell☆111Updated 8 months ago
- [NeurIPS 2025 Spotlight] Official implementation of the SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alig…☆148Updated 2 months ago
- Official code for the paper: Can3Tok (ICCV2025)☆39Updated 3 months ago
- [ICLR 2025] MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow☆24Updated 8 months ago
- Public code for XFactor: Introduces the first geometry-free model to achieve true self-supervised / pose-free Novel View Synthesis (NVS) …☆64Updated last month
- Official implementation of GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs.☆65Updated 5 months ago
- Self-reimplemented version of 4D-LRM.☆63Updated 6 months ago
- Official implementation of Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling☆110Updated 2 weeks ago
- Code and data for UniEgoMotion (ICCV 2025)☆34Updated last month
- [ARXIV’25] Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control☆86Updated 5 months ago
- WideRange4D: Enabling High-Quality 4D Reconstruction with Wide-Range Movements and Scenes☆104Updated 8 months ago
- [NeurIPS 24] The implementation and dataset of LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Rendering and…☆56Updated 8 months ago
- [Neurips DB 2025] PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding☆84Updated last month
- Code for MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data (CVPR 2025)☆195Updated 6 months ago
- The official implementation for "Recollection from Pensieve: Novel View Synthesis via Learning from Uncalibrated Videos".☆49Updated 6 months ago
- [ICLR 2025] Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation☆43Updated 9 months ago
- Trace Anything: Representing Any Video in 4D via Trajectory Fields☆425Updated last month