For which two workloads can you use computer vision? Each correct answer presents a complete solution. NOTE: Each correct selection is worth one point.

Creating photorealistic images from 3D models falls under computer graphics or rendering, not typically computer vision which focuses on understanding existing images.

Assigning the color pixels in an image to object names describes semantic segmentation, a core computer vision task where each pixel is classified as belonging to a specific object or category. This allows for precise understanding of object boundaries within an image.

Describing the contents of an image is a fundamental capability of computer vision, where services can generate human-readable captions that summarize the main objects, actions, and scenes depicted in an image. This provides a high-level understanding of the image.

Detecting inconsistencies and anomalies in a stream of data is a task for anomaly detection services, which can apply to various data types, but not specifically to computer vision unless the "data" is a stream of images being monitored for visual anomalies.

Creating visual representations of numerical data is data visualization, not a core computer vision workload.