About Segment Anything 3 - Video
Segment Anything 3 - Video is a vision model designed for video object segmentation and tracking.
It excels in detecting, segmenting, and tracking objects across video frames using text prompts, points, boxes, masks, or exemplars, with memory mechanisms that propagate predictions while handling occlusions and re-appearances.
Some other noteworthy features of Segment Anything 3 - Video include real-time streaming processing, interactive refinement across frames, and support for concept-driven detection in complex scenes.
Ready to build with Segment Anything 3 - Video?
Try Segment Anything 3 - Video in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/videos/generate \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "sam-3-video",
"input_video": "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/winter_summer_ox.mp4",
"prompt": "the ox horns",
"apply_mask": true
}'Request parameters
Every field Segment Anything 3 - Video accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/videos/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
input_video | stringuri | Yes | — | Video to use as reference. |
prompt | string | Yes | — | Text description of what you want to segment out of the video. |
apply_mask | boolean | No | true | Apply the mask on the image. |