Optimized Minimal 3D Gaussian Splatting

JavaScript Gaussian Splatting library.

Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

📷 Camera-controlled text-to-video generation, now with intrinsics, distortion and orientation control!

WorldPlay: Interactive World Modeling with Real-Time Latency and Geometric Consistency

Sharp Monocular View Synthesis in Less Than a Second

Code for MetaMorph Multimodal Understanding and Generation via Instruction Tuning

VGGT-X: When VGGT Meets Dense Novel View Synthesis

"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training" official implementation.

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

NumPy & SciPy for GPU

cuTile is a programming model for writing parallel kernels for NVIDIA GPUs

CUDA Templates and Python DSLs for High-Performance Linear Algebra

Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

The official implementation of the paper “VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction.”

Code implementation of the paper "World-in-World: World Models in a Closed-Loop World"

A tool for running and customizing real-time, interactive generative AI pipelines and models

[NeurIPS 2025] PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation

Code for ICCV'2025 (Best student paper honorable mention) "RayZer: A Self-supervised Large View Synthesis Model"

[ArXiv 2025] A survey about controllable video generation: This repo is the official awesome of "Controllable video generation: A survey"

Public code for XFactor: Introduces the first geometry-free model to achieve true self-supervised / pose-free Novel View Synthesis (NVS) by learning transferable latent camera pose representations.

A simulation evaluation platform for DROID

Code repo for the SIGGRAPH paper "Monocular Online Reconstruction with Enhanced Detail Preservation". Project page https//poiw.github.io/MODP/index.html

Official code implementation of paper "Gradient-Driven Natural Selection for Compact 3D Gaussian Splatting".

Muon is an optimizer for hidden layers in neural networks