Official Implementation of "Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction"

Official implementation of UniSHARP: Universal Sharp Monocular View Synthesis

[CVPR 2026 Highlight & Best Paper of VideoWorldModel Workshop] NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos

Official code implementation for TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

[CVPR'26] TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens

[ICML 2026] 4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere

[CVPR 2026] Official PyTorch Implementation for the "Neural Gabor Splatting: Enhanced Gaussian Splatting with Neural Gabor for High-frequency Surface Reconstruction" paper

Official code, models, and data for Vista4D: Video Reshooting with 4D Point Clouds (CVPR 2026 Highlight)

PyTorch Implementation of EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision

[ICLR 2026] Trace Anything: Representing Any Video in 4D via Trajectory Fields

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

4DGS360: 360° Gaussian Reconstruction of Dynamic Objects from a Single Video

[ICLR 2026] StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams

[ECCV 2026] Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels

[CVPR 2026] PersonaLive! : Expressive Portrait Image Animation for Live Streaming

Project Lyra: Open Generative 3D World Models

Pioneering Automated GUI Interaction with Native Agents

CoWTracker: Tracking by Warping instead of Correlation

AllTracker is a model for tracking all pixels in a video.

Geometry-Grounded Gaussian Splatting

[ICPR 2026] The official repo for "LayerGS: Decomposition and Inpainting of Layered 3D Human Avatars via 2D Gaussian Splatting"

Official implementation of Continuous 3D Perception Model with Persistent State

Advancing Open-source World Models

CoTracker is a model for tracking any point (pixel) on a video.

🎬ActionMesh: A fast video to animated mesh model with unprecedented quality. Generate animated mesh seamlessly importable into any 3D software in less than a minute.