About This Project
A convolutional denoising autoencoder, trained in PyTorch to reconstruct clean images from noisy inputs. The accompanying Streamlit demo shows the noisy input, the reconstruction, and the residual side by side, making the model's behaviour easy to inspect.
Key Features
- Convolutional autoencoder in PyTorch
- End-to-end denoising pipeline
- Interactive Streamlit demo
Technologies
PyTorchComputer VisionPython