NVIDIA Cosmos-Dreams (fka NVIDIA OmniDreams) is a world model that generates photorealistic video for autonomous-driving simulation in real time.
☆295Jul 24, 2026Updated last week
Alternatives and similar repositories for omni-dreams
Users that are interested in omni-dreams are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- high-performance inference and serving library for interactive autoregressive video and world models☆443Updated this week
- InstantNuRec: Feed-Forward 3D Gaussian Reconstruction from Driving Logs☆151Updated this week
- Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models☆519Mar 10, 2026Updated 4 months ago
- WorldEngine: Towards the Era of Post-Training for Autonomous Driving☆479Jul 20, 2026Updated 2 weeks ago
- AlpaSim is an open-source autonomous vehicle simulation platform designed for development and testing of end-to-end AV policies☆1,151Jul 21, 2026Updated 2 weeks ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Official implementation of the paper "HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving"☆407Nov 8, 2025Updated 8 months ago
- Developer Hub for NVIDIA Alpamayo, containing ready-to-use recipes for fine-tuning, reinforcement-learning post-training, quantization, a…☆83Jul 28, 2026Updated last week
- NVIDIA Asset Harvester is a generative AI model for autonomous vehicle simulation that extracts reusable 3D Gaussian assets directly from…☆238Jul 21, 2026Updated last week
- DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images☆557Jan 15, 2026Updated 6 months ago
- HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation☆53Jun 16, 2026Updated last month
- [CVPR 2026 Oral] Learning to Drive via Real-World Simulation at Scale☆314Jul 24, 2026Updated last week
- NVIDIA CoC Autolabeler is an open autolabeling pipeline for autonomous vehicles that generates Chain-of-Causation reasoning labels and me…☆108Jul 20, 2026Updated 2 weeks ago
- A 3DGS framework for omni urban scene reconstruction and simulation.☆1,241Aug 27, 2025Updated 11 months ago
- NVIDIA Alpamayo 1.5 Nano is an open 10B reasoning VLA model for autonomous vehicles with reinforcement-learning enhanced reasoning, navig…☆346Jul 22, 2026Updated last week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control in…☆713Jun 30, 2026Updated last month
- [ICCV 2025] InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models☆137Jan 23, 2026Updated 6 months ago
- OpenLongTail: Generative Scaling of Long-Tail Driving Data☆30Jul 13, 2026Updated 3 weeks ago
- [CVPR2026] UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling☆21Feb 25, 2026Updated 5 months ago
- [ICLR 2026] WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous Driving☆59Mar 31, 2026Updated 4 months ago
- UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving☆223Apr 14, 2026Updated 3 months ago
- [CVPR 2026] Visual Geometry Transformer for Autonomous Driving☆336Jun 10, 2026Updated last month
- Official Code for Epona: Autoregressive Diffusion World Model for Autonomous Driving (ICCV 2025)☆377Jul 22, 2025Updated last year
- 123D: A Unified Library for Multi-Modal Autonomous Driving Data☆376Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- MTGS: Multi-Traversal Gaussian Splatting☆163Jan 29, 2026Updated 6 months ago
- [CVPR 2025] StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models☆330Jan 27, 2026Updated 6 months ago
- Repo of "Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving"☆168Mar 22, 2026Updated 4 months ago
- ☆151Mar 30, 2026Updated 4 months ago
- [CVPR 2026 Highlight & Best Paper of VideoWorldModel Workshop] NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos☆644May 12, 2026Updated 2 months ago
- [ICLR 2026]WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous Driving☆144Mar 31, 2026Updated 4 months ago
- [NeurIPS 2025 Spotlight] ReSim: Reliable World Simulation for Autonomous Driving☆185May 5, 2026Updated 2 months ago
- NVIDIA Alpamayo 1 Nano is an open 10B reasoning VLA model for autonomous vehicles that pairs driving trajectories with Chain-of-Causation…☆1,961Jul 22, 2026Updated last week
- [ICLR2025] A PyTorch implementation for STORM: Spatiotemporal Reconstruction Model for Large-Scale Outdoor Scenes☆364May 22, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- [ECCV 2026] OmniNWM: Omniscient Navigation World Models for Autonomous Driving☆365Jun 18, 2026Updated last month
- (ICLR2025) Enhancing End-to-End Autonomous Driving with Latent World Model☆383Jun 29, 2025Updated last year
- [ICCV 2025] DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving☆464Sep 17, 2025Updated 10 months ago
- Official implementation of Déjà View: Looping Transformers for Multi-View 3D Reconstruction☆407Jun 1, 2026Updated 2 months ago
- Devkit and documentation for the NVIDIA Physical AI Autonomous Vehicles Dataset☆345Jul 22, 2026Updated last week
- [ICLR 2026] Official Implementation of "UniSplat: Unified Spatio-Temporal Fusion via 3D Latent Scaffolds for Dynamic Driving Scene Recons…☆85May 22, 2026Updated 2 months ago
- [CVPR 2025 Oral & Best Paper Finalist] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models☆1,249Jun 28, 2025Updated last year