Researchers from the University of Cambridge have developed an algorithm called Foot Optimisation, using Uncertain Normals for Surface Deformation (FOUND), which improves the reconstruction of 3D foot models from pictures. They have also released a large-scale synthetic dataset of foot images to aid research in this area. The algorithm uses uncertainties and surface normals to enhance the reconstruction process. An optimization strategy using differentiable rendering is also provided, which outperforms current techniques for surface reconstruction. The researchers’ work has been detailed in a paper and project.
The Value of 3D Foot Reconstruction for Health, Fashion, and Fitness Industries
The health, fashion, and fitness industries have a growing need for accurate 3D foot models. These models are useful for shoe shopping, orthotics, and personal health monitoring. However, existing foot reconstruction solutions have limitations. Expensive scanning equipment, phone-based sensors, and generative models all have drawbacks that make them inadequate for precise scanning in a domestic setting.
The Solution: Foot Optimisation using Uncertain Normals for Surface Deformation (FOUND)
Researchers from the University of Cambridge have developed an algorithm called FOUND to address the limitations of existing foot reconstruction methods. FOUND uses uncertainties and per-pixel surface normals to improve upon conventional multi-view reconstruction optimization approaches. It requires only a minimal number of calibrated RGB photographs as input.
Main Contributions of the Research
- SynFoot Dataset: The researchers have released a large-scale synthetic dataset of 50,000 photorealistic foot pictures with precise silhouettes, surface normal, and keypoint labels. This dataset aids in research on 3D foot reconstruction and exhibits great scalability.
- Uncertainty-Aware Network: The researchers demonstrate that an uncertainty-aware surface normal estimate network can generalize to actual foot pictures after training on synthetic data. This reduces the domain difference between artificial and authentic foot photos.
- Optimization Strategy: The researchers provide an optimization strategy that uses differentiable rendering to fit a generative foot model to a series of calibrated photos. This pipeline outperforms state-of-the-art photogrammetry for surface reconstruction and can rebuild a watertight mesh from a limited number of views.
How AI Can Evolve Your Company
If you want to stay competitive and evolve your company with AI, consider the University of Cambridge’s dataset and AI library for foot reconstruction. AI can redefine your way of work by automating processes and improving customer engagement. To get started, follow these steps:
- Identify Automation Opportunities: Locate key customer interaction points that can benefit from AI.
- Define KPIs: Ensure your AI endeavors have measurable impacts on business outcomes.
- Select an AI Solution: Choose tools that align with your needs and provide customization.
- Implement Gradually: Start with a pilot, gather data, and expand AI usage judiciously.
For AI KPI management advice and continuous insights into leveraging AI, connect with us at hello@itinai.com or stay tuned on our Telegram channel t.me/itinainews or Twitter @itinaicom.
Spotlight on a Practical AI Solution: AI Sales Bot
Consider using the AI Sales Bot from itinai.com/aisalesbot. This bot is designed to automate customer engagement 24/7 and manage interactions across all customer journey stages. Discover how AI can redefine your sales processes and customer engagement by exploring solutions at itinai.com.
