Intel Labs Advances Computer Vision Development with Two New AI Models
March 24, 2023 | IntelEstimated reading time: 2 minutes

Depth estimation is a challenging computer vision task required to create a wide range of applications in robotics, augmented reality (AR) and virtual reality (VR). Existing solutions often struggle to correctly estimate distances, which is a crucial aspect in helping plan motion and avoiding obstacles when it comes to visual navigation. Researchers at Intel Labs are addressing this issue by releasing two AI models1 for monocular depth estimation: one for visual-inertial depth estimation and one for robust relative depth estimation (RDE).
The latest RDE model, MiDaS version 3.1, predicts robust relative depth using only a single image as an input. Due to its training on a large and diverse dataset, it can efficiently perform on a wider range of tasks and environments. The latest version of MiDaS improves model accuracy for RDE by about 30% with its larger training set and updated encoder backbones.
MiDaS has been incorporated into many projects, most notably Stable Diffusion 2.0, where it enables the depth-to-image feature that infers the depth of an input image and then generates new images using both the text and depth information. For example, digital creator Scottie Fox used a combination of Stable Diffusion and MiDaS to create a 360-degree VR environment. This technology could lead to new virtual applications, including crime scene reconstruction for court cases, therapeutic environments for healthcare and immersive gaming experiences.
Intel Introduces MiDaS 3.1 for Computer Vision
While RDE has good generalizability and is useful, the lack of scale decreases its utility for downstream tasks requiring metric depth, such as mapping, planning, navigation, object recognition, 3D reconstruction and image editing. Researchers at Intel Labs are addressing this issue by releasing VI-Depth, another AI model that provides accurate depth estimation.
VI-Depth is a visual-inertial depth estimation pipeline that integrates monocular depth estimation and visual-inertial odometry (VIO) to produce dense depth estimates with a metric scale. This approach provides accurate depth estimation, which can aid in scene reconstruction, mapping and object manipulation.
Incorporating inertial data can help resolve scale ambiguity. Most mobile devices already contain inertial measurement units (IMUs). Global alignment determines appropriate global scale, while dense scale alignment (SML) operates locally and pushes or pulls regions toward correct metric depth. The SML network leverages MiDaS as an encoder backbone. In the modular pipeline, VI-Depth combines data-driven depth estimation with the MiDaS relative depth prediction model, alongside the IMU sensor measurement unit. The combination of data sources allows VI-Depth to generate more reliable dense metric depth for every pixel in an image.
Suggested Items
Singular Photonics Emerges from Stealth with Portfolio of SPAD-based Image Sensors
01/23/2025 | PRNewswireSingular Photonics emerged from stealth mode today, launching a new generation of image sensors based on single photon avalanche diodes (SPADs). A spin-out from the University of Edinburgh lab of digital imaging pioneer
INSPECTIS AB Partners with Sony ISS to Launch Series U50 Digital Camera Microscope
01/09/2025 | INSPECTIS ABINSPECTIS AB has partnered with Sony Image Sensing Solutions to develop the Series U50 digital camera microscope, featuring an impressive 4K resolution and a 60 FPS frame rate.
Imec, Partners Unveil SWIR Sensor with Lead-free Quantum Dot Photodiodes
12/31/2024 | ImecAt the 2024 IEEE International Electron Devices Meeting (IEDM), imec, a world-leading research and innovation hub in nanoelectronics and digital technologies, and its partners in the Belgian project Q-COMIRSE, present a first of its kind prototype shortwave infrared image sensor with indium arsenide quantum dot photodiodes.
NTT, Olympus Joint Demonstration Shows IOWN APN's Low-latency Capability
11/21/2024 | JCN NewswireNTT Corporation and Olympus Corporation announced that, following the start of their joint experiment in March of the world’s first cloud endoscope system which processes endoscopic videos on the cloud, they jointly established a cloud endoscopy system utilizing the IOWN APN technology.
MVTec Makes Machine Vision Software Even Easier to Use
10/16/2024 | MVTec Software GmbHMVTec Software GmbH, a leading global manufacturer of machine vision software, is launching version 5.6 of MVTec MERLIC on October 16, 2024. MERLIC is an intuitive no-code software that enables even users with little experience in machine vision to quickly achieve success.