MediaPipe
PulseAugur coverage of MediaPipe — every cluster mentioning MediaPipe across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
AR hand pose estimation accurate for impaired hands
A new study published on arXiv investigates the accuracy of hand pose estimation in augmented reality (AR) applications, particularly for individuals with hand impairments. Researchers compared the HoloLens 2 HMD with s…
-
Open-source EyeTheia toolbox offers webcam-based gaze estimation
Researchers have developed EyeTheia, an open-source, lightweight deep learning pipeline for gaze estimation using standard webcams. The system combines landmark extraction with a convolutional neural network, offering r…
-
AI system offers real-time athletic performance analysis
Researchers have developed a lightweight prototype for real-time athletic performance analysis using markerless deep learning. The system integrates Human Pose Estimation (HPE) with exercise-specific logic to provide AI…
-
Open-source AI meeting platform Hoovik faces real-time inference challenges
Anupam Kumar, the creator of the open-source AI meeting platform Hoovik, found that the most challenging aspect of development was not the core WebRTC technology but managing real-time multimodal AI inference. This invo…
-
AI game "Hand Gesture at Doc Yang" uses MediaPipe for live hand tracking
A new browser-based game called "Hand Gesture at Doc Yang" utilizes AI, specifically MediaPipe, to detect and interpret live hand gestures. Players can score points by displaying two hand gestures simultaneously, with e…
-
ProxyFace adds local, emotional avatars to AI chats
ProxyFace is an open-source project that adds a local, expressive avatar to AI interactions. It utilizes a small, on-device emotion model and eye-tracking to make the avatar react to AI output and the user's gaze. The p…
-
AI research targets efficient, accessible sign language translation
Two new research papers explore advancements in sign language translation (SLT) technology, focusing on making systems more efficient and accessible for low-resource languages. One paper proposes a data-centric approach…
-
Tamaththul3D creates high-fidelity 3D Saudi Sign Language avatars from video
Researchers have developed Tamaththul3D, a novel pipeline for generating high-fidelity 3D avatars of Saudi Sign Language (SSL). This system addresses a significant gap in resources for Arabic Sign Language (ArSL), which…
-
Google Snapseed adds on-device AI object editing
Google AI has introduced a new on-device image segmentation feature for its Snapseed photo editing app, called Object Brush. This feature allows users to intuitively select and edit specific objects within an image by s…
-
Google details real-time AI effects pipeline for YouTube Shorts
Google has detailed its approach to enabling real-time generative AI effects on YouTube Shorts by optimizing large models for mobile devices. The company employs knowledge distillation, where a powerful but slow "teache…