vsitzmann/siren

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1993 stars · 272 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Official PyTorch implementation of SIREN, a neural network architecture using periodic (sine) activation functions for implicit neural representations of images, audio, video, and signed distance functions. Includes experiment scripts, differential operators, and a Colab notebook for interactive exploration.

Use cases

• fit a neural network to an image or audio signal
• learn implicit neural representations of shapes and point clouds
• solve Poisson's equation with a neural network
• reproduce SIREN paper experiments
• experiment with periodic activation function initialization

When to choose

• you need to represent continuous signals like images, audio, or SDFs with a small neural network
• you want the reference implementation of the SIREN paper
• you're researching coordinate-based networks and activation function design

When to avoid

• you need a production-ready, actively maintained library
• you want general-purpose computer vision or audio processing tools
• you need a framework for standard feedforward or convolutional networks

Facets

library · maturity maintenance

machine-learning deep-learning image-processing audio-processing simulation deep-learning computer-vision graphics python implicit-neural-representations siren neurips-paper signal-representation research-code research gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="vsitzmann/siren")