DesAiN – 3D Customizer Application is an innovative platform designed to transform the traditional approach to digital design by moving beyond static 2D tools. It offers an interactive, intelligent 3D customization environment accessible through a web interface. The system addresses the limitations of manual workflows and lack of personalization in existing design tools. Using technologies like Three.js, FastAPI, and Python, and integrating Generative Adversarial Networks (GANs), DesAiN allows users to: Generate AI-based textures (like leather, wood, and metal), Predict optimal placements for elements such as logos and text using Conditional GANs, Interact with a built-in design assistant chatbot (Desy) powered by LSTM and NLP for real-time suggestions. The platform also includes features like: Live 3D preview and editing, Text/logo overlays, QR code integration for interactivity, Project management capabilities to save, load, and export designs. The dataset for training includes manually labeled data such as object positions, rotations, and surface normals to improve AI accuracy. DesAiN envisions a full design ecosystem that empowers creators—from startups to marketers—to turn digital designs into real-world products. Its future roadmap includes collaborative tools, enterprise branding kits, plugin support, document generation, and complete product fulfillment workflows. In essence, DesAiN is not just a 3D customizer—it’s a leap toward democratizing intelligent 3D design for everyone.
15 Jun 2025
Problem: Network outages and equipment failures can have severe consequences, including financial losses, disrupted services, and reputational damage. Traditional maintenance approaches are reactive, addressing issues only after they occur. This leads to inefficiencies, increased costs, and prolonged downtime. There is a critical need for a proactive solution that predicts potential failures and enables timely interventions solution:ProactiveGuard is a cutting-edge predictive maintenance system designed to revolutionize how organizations manage their infrastructure. The system integrates operational data (e.g., sensor readings), connectivity metrics (e.g., network performance), and geospatial data (e.g., location-based environmental factors) to predict failures before they happen. Key features of ProactiveGuard include: Real-Time Risk Prediction : Uses machine learning models to analyze historical and real-time data, providing accurate predictions of failure probabilities. Geospatial Insights : Incorporates location-specific data to identify patterns and correlations between environmental conditions and equipment performance. Actionable Alerts : Generates risk levels (Low, Medium, High) and actionable recommendations to guide maintenance teams. Scalable Architecture : Built with a modular design to support integration with IoT devices, APIs, and third-party systems.
2 Mar 2025
Problem Statement: People with motor disabilities struggle to use digital devices. Voice commands are slow, and existing hardware solutions are expensive. 💡 Solution: An AI-powered eye-tracking cursor using IBM Granite Vision Transformer to enable hands-free control of PCs and smartphones with just eye movements and blinks. 🚀 Key Features: ✅ Gaze-Based Cursor Movement – Move the cursor by looking around. ✅ Blink to Click – Short blink for left-click, long blink for right-click. ✅ Gaze Scrolling – Look up/down to scroll pages and reels. ✅ Real-Time AI Adaptation – Model learns user-specific gaze patterns. ✅ No Extra Hardware Needed – Works with a standard webcam.
23 Feb 2025
.png&w=256&q=75)
.png&w=640&q=75)
