Starred repositories
PlenOctree Volume Rendering (supports CUDA & fragment shader backends)
Code for KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs
A curated list of awesome neural radiance fields papers
Github repository for dense neural SLAM leveraging joint uncertainty learning
[CVPR 2023] vMAP: Vectorised Object Mapping for Neural Field SLAM
Co-Fusion: Real-time Segmentation, Tracking and Fusion of Multiple Objects
MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects
[ICCV'23] Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis
This is the official code release for SPARF: Neural Radiance Fields from Sparse and Noisy Poses [CVPR 2023-Highlight]
Fourier Modal Method for multilayer metamaterials. Mirror of https://gitlab.com/nannos/nannos
Integrated photonic simulation framework established by Hezq
Continuous Adjoint Optimization with Lumerical, developed at UC Berkeley
Lumerical scripts for rapid geometry and simulation definition, bash scripts for remote-host Lumerical execution, and MATLAB scripts for Lumerical script generation and analysis.
A collection of Python scripts designed to interface with the Lumerical Design Suite.
Python based continuous adjoint optimization wrapper for Lumerical
Package for KLayout to add integrated optics / silicon photonics functionality (waveguides, netlist extraction, circuit simulations, etc)
A simulator for photonic integrated circuits.
Flexible simulation package for optical neural networks
18.369/8.315 - Mathematical Methods in Nanophotonics course
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.
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Tools for shrinking fastText models (in gensim format)
Yet another common Python wrapper for Alice and Salut skills and bots in Telegram, VK, and Facebook
SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.
Source code and demo for memory bank and SiliconFriend
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Robust Speech Recognition via Large-Scale Weak Supervision