Lists (8)
Stars
🚀 Efficient implementations of state-of-the-art linear attention models
NVIDIA Math Libraries for the Python Ecosystem
[TMLR 2025] Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields
Official Repo for Fovea Stacking: Imaging with Dynamic Localized Aberration Correction
Differentiable signal processing on the sphere for PyTorch
A curated collection of fun and creative examples generated with Nano Banana🍌, Gemini-2.5-flash-image based model. We also release Nano-consistent-150K openly to support the community's development…
[SIGGRAPH 2025] Official Repository for Collaborative On-Sensor Array Cameras
3D multi-source electromagnetic simulations in frequency domain, implementing the augmented partial factorization (APF) and other methods.
A fast communication-overlapping library for tensor/expert parallelism on GPUs.
varRCWA algorithm implementation with GPU support
Turn SymPy expressions into trainable JAX expressions.
Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/
PyTorch implementation of the fractional Fourier transform with trainable transform order.
Super fast MATLAB + CUDA/C++ Fourier ptychographic solver
Noise Modeling in One Hour: Minimizing Preparation Efforts for Self-supervised Low-Light RAW Image Denoising
Comprehensive optical design, optimization, and analysis in Python, including GPU-accelerated and differentiable ray tracing via PyTorch.
Official implementation of Ring Deconvolution Microscopy from https://www.nature.com/articles/s41592-025-02684-5
Library for reading and processing ML training data.
Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023
Differentiable Finite Element Method with JAX
Code for the paper: Image-guided computational holographic wavefront shaping. https://doi.org/10.1038/s41566-024-01544-6.
Wraps PyTorch code in a JIT-compatible way for JAX. Supports automatically defining gradients for reverse-mode AutoDiff.
Distributed Compiler based on Triton for Parallel Systems
RCWA for optical metrology and metasurfaces
Python package for high-performance spatial light modulator (SLM) control and holography. Supports features from aberration-corrected 3D point clouds to automated Fourier-domain calibrations.
A program using pytorch to simulate diffracive deep nerual network (D2NN), containing updates (relative to the original paper) of incoherent propagation, parallel computation, nonlinear activation,…