🧠 neural-imaging-python

A coordinate-based neural network that learns to generate images from scratch using only (x, y) inputs and RGB outputs. This project explores neural representations of images, inspired by architectures like SIREN and NeRF.

---

🎥 Demos

📊 Calculator Image (Neural Approximation)

🌄 Boathouse Timelapse

📺 For more examples

---

🚀 Features

• Simple coordinate-to-color MLP architecture
• Custom training loop using PyTorch
• Flexible image resolution and sampling
• Support for grayscale and RGB targets
• Visualized output directly in training
• Timelapse image generation demos

---

📦 Setup

1. Clone the repository:

   git clone https://github.com/curtis-aln/neural-imaging-python.git
   cd neural-imaging-python