visionfamily
MediaPipe vision models
Google on-device vision models behind the MediaPipe solutions for faces, hands, pose, gestures and segmentation; run on phones, browsers and microcontrollers.
Levelfamily
Classvision
Parametersnot in the notes
Contextnot in the notes
Releasednot in the notes
Opennessunknown
Runs onmobile or NPU, microcontroller
Statusactive
Lineage
1 member has no release date in the notes, so it is not on this timeline.
MediaPipe Iris belongs to this familyvision19 Jun 2020MediaPipe Hands belongs to this familyvision18 Jun 2020BlazePose GHUM belongs to this familyvision17 Jun 2020Face Mesh belongs to this familyvision15 Jul 2019BlazeFace belongs to this familyvision11 Jul 2019MediaPipe Selfie Segmenter belongs to this familyvisionWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.
R&D Topics
Identity
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- CNN
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- BlazeFace, BlazePose GHUM, Face Mesh V2 with blendshapes, Hands, Iris, gesture recogniser, selfie, hair and multiclass segmenters, interactive segmenter, holistic landmarker, object detector.
- Context length
- not in the notes
- Input
- image
- Output
- labels and boxes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- unknown
- Licence
- not in the notes sources
- Access routes
- open weights download, cloud marketplace
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- mobile or NPU, microcontroller
- Footprint
- Edge or toolkit builds listed in: Qualcomm AI Hub, MediaPipe, STM32 model zoo, NXP eIQ model zoo.
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Industry Use Cases
No industry use case links this model.
Links
DeveloperGooglebig tech, USA
Googlebig tech, USAModelMediaPipe vision modelsGoogle, vision
MediaPipe vision modelsGoogle, visionR&D TopicsHuman Pose EstimationFace Detection, Recognition and LivenessEfficient Vision Networks for Mobile and Edge Devices
Use Casesnone recorded
Who Runs Itnone recorded
Models 6
Organisations 1
R&D topics 3
Efficient Vision Networks for Mobile and Edge DevicesSmall, fast vision networks, often found by architecture search, that run on phones, came…produced byHuman Pose EstimationLocating body, hand and face keypoints of people in images and video.produced byFace Detection, Recognition and LivenessFinding faces, verifying identity, and checking attributes, gaze or spoofing for identity…produced by
Sources
- ai.google.dev/edge/mediapipe/solutions/guide https://ai.google.dev/edge/mediapipe/solutions/guide
- github.com/GoogleCloudPlatform/vertex-ai-samples/tree/ma... https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/community/model_garden
- aihub.qualcomm.com/models/mediapipe_face https://aihub.qualcomm.com/models/mediapipe_face
- github.com/zmurez/MediaPipePyTorch https://github.com/zmurez/MediaPipePyTorch/
- github.com/STMicroelectronics/stm32ai-modelzoo/tree/main... https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/face_detection/facedetect_front
- github.com/STMicroelectronics/stm32ai-modelzoo/tree/main... https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/pose_estimation
- github.com/NXP/eiq-model-zoo/tree/main/tasks/vision/sema... https://github.com/NXP/eiq-model-zoo/tree/main/tasks/vision/semantic-segmentation
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "MediaPipe Vision Models", https://aurion.semai.id/models/google-mediapipe/, records of October 2026.