Latest

• Déjà View: Looping Transformers for Multi-View 3D Reconstruction
• Asset Harvester: Extracting 3D Assets from Autonomous Driving Logs for Simulation
• TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens
• Lyra 2.0: Explorable Generative 3D Worlds
• Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation
• ViPE: Video Pose Engine for 3D Geometric Perception
• Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos