Stars
Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
[CVPR 2026] InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields
Code Implementation of "WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation"
Seoul World Model: Grounding World Simulation Models in a Real-World Metropolis
[CVPR 2026] Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching
Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence
[CVPR 2026 Highlight] Offical code for "FastGS: Training 3D Gaussian Splatting in 100 Seconds"
Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels
Dense matching library based on PyTorch
π RuView: WiFi DensePose turns commodity WiFi signals into real-time human pose estimation, vital sign monitoring, and presence detection — all without a single pixel of video.
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Self-reimplemented version of Long-LRM.
[CVPR 2026] tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction
[CVPR'26 Demo] Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device
Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals
Official repository for Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs
[CVPR2026]🚀🚀🚀Official code for the paper "YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection." *(YOLO = You Only Look Once)* 🔥🔥🔥
VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
[TVCG2024] PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction
✨ An advanced 3D Gaussian Splatting renderer for THREE.js
A cross-platform, high performance renderer for Gaussian Splatting using Vulkan Compute. Supports Windows, Linux, macOS, iOS, and visionOS
[3DV'25] 3D Reconstruction with Spatial Memory
Real-Time Probabilistic Dense Monocular SLAM Using Compact Code Representation
[CVPR 2025 Highlight] Real-time dense scene reconstruction with SLAM3R