SCoPE: Sightline-Coordinate Positional Encoding for 3D-Aware Video Generation

Official repository for Beyond Pixels: From Video Priors to 4D Worlds.

[CVPR 2026] Official implementation for the paper "Stabilizing Streaming Video Geometry via Dynamic Feature Normalization".

Official implementation of Video-DPM

[SIGGRAPH 2026] Pixal3D: Pixel-Aligned 3D Generation from Images

From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models (ReChannel)

[Tech Report] A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing

[ECCV 2026] One Video, One World: Turning Monocular Video into Physical 4D Scenes

Vision Bridge Transformer at Scale

[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++

Official repo of "FlowWAM: Optical Flow as a Unified Action Representation for World Action Models"

PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space

[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

An unofficial Chrome extension that brings Codex conversations, project context, file/line references, and safe LaTeX edits into the Overleaf source editor.

[ECCV 2026]Official implementation of the paper: "FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry"

Official implementation of SceneFrom3D

[ICLR'26] Official implementation of "3D Scene Prompting for Scene-Consistent Camera-Controllable Video Generation"

ViGeo: Towards Consistent Video Geometry Estimation

Project Lyra: Open Generative 3D World Models

Code for "FlashWorld: High-quality 3D Scene Generation within Seconds" (ICLR 2026 Oral)

[ECCV 2026] WorldMesh: Generating Navigable Multi-Room 3D Scenes via Mesh-Conditioned Image Diffusion

[SIGGRAPH Asia 2025] WorldExplorer: Towards Generating Fully Navigable 3D Scenes

[CVPR 2026] Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction

OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder

Official implementation of UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception (ECCV 2026).

Official Implementation of MultiWorld: Scalable Multi-Agent Multi-View Video World Models

Implementation of Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players