CVL-UESTC/IGA-INR

ICML2025-Inductive Gradient Adjustment for Spectral Bias in Implicit Neural Representations

21
/ 100
Experimental

This project offers a method to improve the quality of images and 3D shapes generated by Implicit Neural Representations (INRs). It takes raw data for images or 3D models and helps INRs learn fine details like textures and edges more effectively. This is particularly useful for researchers and practitioners working with neural networks to reconstruct or generate high-fidelity visual content.

No commits in the last 6 months.

Use this if you are training Implicit Neural Representations (INRs) and need to capture high-frequency details, such as sharp textures and intricate edges, more accurately in your generated images or 3D models.

Not ideal if your primary goal is general neural network training that doesn't specifically involve Implicit Neural Representations for high-fidelity content generation.

3D-reconstruction image-synthesis computer-vision neural-rendering
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 3 / 25

How are scores calculated?

Stars

47

Forks

1

Language

Jupyter Notebook

License

Last pushed

May 31, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/CVL-UESTC/IGA-INR"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.