The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Kolmogorov Arnold Networks

Segment Anything in Medical Images

NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to the Convolutional Layers, changing the classic linear transformation of the convolution to learna…

This project is the official implementation of 'Diffir: Efficient diffusion model for image restoration', ICCV2023

FastKAN: Very Fast Implementation of Kolmogorov-Arnold Networks (KAN)

computational zoom from raw sensor data

Local Texture Estimator for Implicit Representation Function, in CVPR 2022

A More Fair and Comprehensive Comparison between KAN and MLP

Code for WWW-20 Paper: HTML: Hierarchical Transformer-based Multi-task Learning for Volatility Prediction

A multi-contrast multi-repetition multi-channel MRI k-space dataset for low-field MRI research

Learning Local Implicit Fourier Representation for Image Warping, in ECCV 2022

Kolmogorov-Arnold Networks (KAN) using Jacobi polynomials instead of B-splines.

Kolmogorov-Arnold Networks (KAN) using orthogonal polynomials instead of B-splines.

This code implements a Radial Basis Function (RBF) based Kolmogorov-Arnold Network (KAN) for function approximation.

SineKAN: Kolmogorov-Arnold Networks Using Sinusoidal Activation Functions