Compare object detection and panoptic segmentation

What it covers

• Run object detection to get bounding boxes and labels
• Run panoptic segmentation to get pixel-level masks
• Visualize and compare outputs side-by-side

What it uses

Install

terminal

$pip install pixeltable torch transformers timm

Pixeltable calls

huggingface.()vision.bboxes_draw()vision.overlay_segmentation()pxt.create_table()insert()add_computed_column()

A look at the code

images.add_computed_column(
    detections=detr_for_object_detection(
        images.image, model_id='facebook/detr-resnet-50', threshold=0.8
    )
)

One cell of the notebook, copied as it is. Open it in Colab for the rest.

• Visualize object detections

  Draw bounding boxes on images to visualize object detection results.

  Updated Oct 13, 2026Open in Colab

• Promptable segmentation with SAM 3

  Segment every object matching a concept (a short text phrase or a bounding box) using Meta's Segment Anything Model 3.

  Updated Sep 25, 2026Open in Colab

• Generate captions for images

  Automatically create descriptive captions for images using AI vision models.

  Updated Apr 10, 2026Open in Colab

• Transform images with AI-powered editing

  You have a batch of images that need AI-powered transformations—like turning photos into paintings, adding stylistic effects, or modifying content based on text prompts.

  Updated Apr 10, 2026Open in Colab