diff --git a/README.md b/README.md index a0a5cf93b..97d727466 100644 --- a/README.md +++ b/README.md @@ -5,6 +5,8 @@ ![Real-time Face Detection](mediapipe/docs/images/realtime_face_detection.gif) +> "MediaPipe has made it extremely easy to build our 3D person pose reconstruction demo app, facilitating accelerated neural network inference on device and synchronization of our result visualization with the video capture stream. Highly recommended!" - George Papandreou, CTO, [Ariel AI](https://arielai.com) + ## ML Solutions in MediaPipe * [Hand Tracking](mediapipe/docs/hand_tracking_mobile_gpu.md) diff --git a/mediapipe/models/README.md b/mediapipe/models/README.md index 80aca046a..1d67d918c 100644 --- a/mediapipe/models/README.md +++ b/mediapipe/models/README.md @@ -3,19 +3,22 @@ Here are descriptions of the models used in the [example applications](../docs/examples.md). ### Object Detection -For details on the models, see [here](object_detection_saved_model/README.md). + * [TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/models/ssdlite_object_detection.tflite) + * See [here](object_detection_saved_model/README.md) for model details. - * [Object Detection on Desktop](../docs/object_detection_desktop.md) - * [Object Detection on GPU on Android](../docs/object_detection_android_gpu.md) - * [Object Detection on CPU on Android](../docs/object_detection_android_cpu.md) +### Face Detection + * [TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/models/face_detection_front.tflite) + * Paper: ["BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs"](https://sites.google.com/corp/view/perception-cv4arvr/blazeface) + * [Model card](https://sites.google.com/corp/view/perception-cv4arvr/blazeface#h.p_21ojPZDx3cqq) -### BlazeFace face detection model - * [TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/models/face_detection_front.tflite) - * Paper: ["BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs"](https://sites.google.com/corp/view/perception-cv4arvr/blazeface) - * Model card: [BlazeFace model card](https://sites.google.com/corp/view/perception-cv4arvr/blazeface#h.p_21ojPZDx3cqq) - -### Hair segmentation model - * [TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/models/hair_segmentation.tflite) - * Paper: ["Real-time Hair segmentation and recoloring on Mobile GPUs"](https://sites.google.com/corp/view/perception-cv4arvr/hair-segmentation) - * Model card: [Hair segmentation model card](https://sites.google.com/corp/view/perception-cv4arvr/hair-segmentation#h.p_NimuO7PgHxlY) +### Hand Detection and Tracking + * [Palm detection TfLite model](https://github.com/google/mediapipe/tree/master/mediapipe/models/palm_detection.tflite) + * [2D hand landmark TfLite model](https://github.com/google/mediapipe/tree/master/mediapipe/models/hand_landmark.tflite) + * [3D hand landmark TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/models/hand_landmark_3d.tflite) + * [Google AI Blog post](https://mediapipe.page.link/handgoogleaiblog) + * [Model card](https://mediapipe.page.link/handmc) +### Hair Segmentation + * [TFLite model](https://github.com/google/mediapipe/tree/master/mediapipe/models/hair_segmentation.tflite) + * Paper: ["Real-time Hair segmentation and recoloring on Mobile GPUs"](https://sites.google.com/corp/view/perception-cv4arvr/hair-segmentation) + * [Model card](https://sites.google.com/corp/view/perception-cv4arvr/hair-segmentation#h.p_NimuO7PgHxlY)