Computer Vision

Teaching machines to see — image recognition, detection, and visual understanding.

Image Classification

Recognizing and categorizing images using deep learning architectures.

Object Detection

Locating and identifying objects within images and video streams.

Image Segmentation

Pixel-level classification, semantic and instance segmentation techniques.

Video Understanding

Action recognition, video captioning, and temporal visual reasoning.

Depth estimation, point clouds, NeRFs, and 3D scene understanding.

Image Generation

Style transfer, super-resolution, inpainting, and neural rendering.

Face Recognition

Face detection, verification, identification, and facial attribute analysis.

Pose Estimation

Human body pose, hand tracking, and skeleton detection from images.

Visual Question Answering

VQA, image captioning, and reasoning about visual content with language.

Medical Imaging

AI for radiology, pathology, retinal scans, and clinical image analysis.