3D Reconstruction

Pose Estimation

The computer vision task of detecting the position and orientation of a person's body joints in images or video.

Point Cloud

A set of data points in 3D space, typically generated by LiDAR or depth sensors, representing surface geometry.

Visual SLAM

Simultaneous Localisation and Mapping using visual sensors to build a map while tracking position within it.

A unified approach combining semantic and instance segmentation to provide complete scene understanding.

Partitioning an image into multiple segments or regions, assigning each pixel to a specific class or object.

Identifying and locating specific objects within an image by drawing bounding boxes around them.

The process of aligning two or more images of the same scene taken at different times, viewpoints, or by different sensors.

Classifying every pixel in an image into a predefined category without distinguishing between individual object instances.

Predicting the distance of surfaces in a scene from the camera viewpoint using visual information.

The field of AI that enables computers to interpret and understand visual information from images and video.

Enhancing the resolution and quality of images beyond their original pixel count using AI techniques.