Amruta Purandare

Category: Projects

  • Facial Expressions

    Detecting Facial Expressions of Comedians Captures facial landmark points using OpenCV + DLib library in Python Real-Time Face Tracking with TensorFlow.JS Captures live stream from camera and runs TensorFlow.JS FaceMesh model to capture facial landmark points in real-time.. Animate Facial Expressions into 3D Characters Implemented using Lens Studio from Snap Chat.. Uses AI + ML…

  • Mixed Reality

    Augmented Reality using Markers in A-Frame + 3D Model from SketchFab Honey, I Shrunk This Guy A tiny person dancing on my desk.. Visitor from Lilliput Combining Augmented / Mixed Reality with Hand-Tracking ML and 3D Animation House Warming Guest Placing 3d model in live scene Virtual Trial-Room Design + Customize clothes by selecting colors,…

  • Masterchef AI

    Custom ML model to classify food / menu images, using Teachable Machines .. Demo Video Sample Output What’s Next: Try confusing the classifier by adding similar class labels, e.g. spaghetti / pasta / noodles, or juice / milkshake etc. Use Generative Neural Nets (GANs) to generate new innovative dishes or recipes..

  • Computational Music

    MIDI Parser + Visualizer Parses MIDI file by extracting notes, and shows how to play the tune on piano, by highlighting corresponding keys.. Music Generation using Hand Gestures Each box at (x, y) in the colorful canvas grid produces a sound with frequency f(x, y) using Tone.js library in Java Script. Hand movements are captured…

  • AutoML

    Model built in AutoML Vision to detect popular cartoon characters.. Model built in Auto-ML Vision to recognize popular TV / Movie Characters

  • Deep FAKE

    Converting Still Photos into Talking Videos Here, the still pictures of famous Hollywood actors on the left automatically “lip-sync” the dialog from Shri-420 in the centre to produce the output video on the right.. Converting Still Photos into Talking Animated Characters Here, I first converted still pictures of famous actors into Anime Characters like this:…

  • Hand-Gestures

    Using Hand-Gestures to Move Objects in AR / VR Instead of fixing Aruco Markers on real-world surfaces (like wall, posters, table), here I use hand-tracking model Hand-Pose from TensorFlow.JS to move virtual objects.. Using Hand-Gestures to Generate Music Virtual Visitor from Lilliput Combining Hand-Gestures with Augmented / Mixed Reality and 3D Animation Hand Gesture Recognition…

  • Video Segmentation

    Real-Time Video Segmentation on Live Camera Stream to Extract Person from Background, and replace Background, w/o Hollywood style Green Screen Studio Setup.. Chroma-Key Effect using TensorFlow.JS Try Live on – https://codepen.io/pamruta/full/gOPbLgo Chroma-Key Effect using SparkAR Digital Twins Harnessing the magical super-powers of video segmentation in Lens Studio to create digital twins..

  • Motion Capture

    Capturing body movements, gestures and actions from dance and figure skating videos using OpenPose from CMU’s panoptic studio.. Capturing Live Action (Postures, Gestures, Motion) into 3D Figures

  • Style Transfer

    Applying Neural Style Transfer to produce artistic effects and filters in photos and videos.. Originals: Styled using: Implemented using PyTorch and Keras.. Try in Google Colab or download the Jupyter Notebook from GitHub