YOLO Vision 2026:
On the Ultralytics roadmap

Ultralytics YOLO-Stereo3D

Stereo 3D detection from binocular camera pairs for robotics: a camera-native alternative to lidar, one of the new modalities joining the Ultralytics YOLO family in 2027. Build on YOLO26 today and be ready for what's next.

Trusted by the world's leading organizations

DuolingoShellSiemensRenaultPhilipsNEURA RoboticsMercado LibreTata SteelFlock SafetyIntelDefense Intelligence AgencyDHL
DuolingoShellSiemensRenaultPhilipsNEURA RoboticsMercado LibreTata SteelFlock SafetyIntelDefense Intelligence AgencyDHL
DuolingoShellSiemensRenaultPhilipsNEURA RoboticsMercado LibreTata SteelFlock SafetyIntelDefense Intelligence AgencyDHL

Our models' impact

Streamline processes across industries with our cutting-edge vision AI models. Speed, accuracy and ease-of-use powered by Ultralytics.

GitHubGitHub stars
Downloads
Ultralytics YOLO usages / day
Open-source contributors

The evolution of Ultralytics YOLO models

See how Ultralytics YOLO evolved from the practical YOLOv5 workflow to edge-ready YOLO26 inference.

Made real-time object detection accessible with a fast, practical PyTorch workflow.

Expanded the unified workflow across detection, segmentation, classification, pose, and OBB.

Improved accuracy, speed, and efficiency while preserving the familiar Ultralytics workflow.

Introduced end-to-end inference and an architecture optimized for efficient edge deployment.

Deploy Anywhere

Export to 20 formats and deploy across edge, cloud, and mobile.

Explore industry solutions

See how teams apply Ultralytics computer vision across production environments.

Frequently asked questions

  • YOLO-Stereo3D is an upcoming Ultralytics model announced on the official Ultralytics roadmap for stereo 3D detection from binocular camera pairs in robotics: a camera-native alternative to lidar, and one of the new modalities planned for the YOLO family in 2027.

  • In general, stereo cameras cost a fraction of lidar, add no moving parts, and recover 3D information from paired imagery. That is why the Ultralytics roadmap positions YOLO-Stereo3D as a camera-native alternative to lidar for robotics.

  • The released Ultralytics YOLO-Depth models perform monocular depth estimation from one RGB camera, while the upcoming YOLO-Stereo3D task uses a synchronized binocular camera pair for stereo 3D detection.

  • Release timing is announced on the official Ultralytics roadmap, which lists YOLO-Stereo3D among the new modalities joining the YOLO family in 2027. Follow the roadmap and GitHub for announcements.

  • Use Ultralytics YOLO-Depth when one RGB camera and a dense per-pixel depth map meet your needs. For object detection, segmentation, and pose, start with Ultralytics YOLO26. Both use the production Ultralytics workflow while YOLO-Stereo3D remains on the roadmap.

Be ready for YOLO-Stereo3D

Build camera-based perception on Ultralytics YOLO26 today and adopt stereo 3D detection when it ships.