Learning in infinite dimension with neural operators.

geometric ray tracing for optical systems

Project on using deep models for deconvolution of hyperspectral images with chromatic aberration.

DeepLens: a differentiable ray-tracer for computational lens design.

A toolbox for spectral compressive imaging reconstruction including MST (CVPR 2022), CST (ECCV 2022), DAUHST (NeurIPS 2022), BiSCI (NeurIPS 2023), HDNet (CVPR 2022), MST++ (CVPRW 2022), etc.

free finite-difference time-domain (FDTD) software for electromagnetic simulations

[Optica] Modeling Off-Axis Diffraction with Least-Sampling Angular Spectrum Method

DFlat is a forward and inverse design framework for flat optics. Although specially geared for the design of metasurface optics, it may be used for any end-to-end imaging and sensing task.

A paper list for deep optics design.

Adaptive Weighted Attention Network with Camera Spectral Sensitivity Prior for Spectral Reconstruction from RGB Images in CVPRW 2020 (Winner of NTIRE Challenge, Oral)

Official code repository for the paper: "The Differentiable Lens: Compound Lens Search over Glass Surfaces and Materials for Object Detection"

[ICLR 2023] Factorized Fourier Neural Operators

A spatial-spectral prior deep network for single hyperspectral image super-resolution (IEEE TCI)

Design of optical metasurfaces using MEEP's Adjoint Solver

Exploration of neural network model from "Neural nano-optics for high-quality thin lens imaging" for optimising metasurface design.

浙大钉钉健康自动打卡助手

Code for the CVPR 2022 paper "Quantization-aware Deep Optics for Diffractive Snapshot Hyperspectral Imaging".

Pado: differentiable simulation of light waves

Repository for "Neural Nano-Optics for High-quality Thin Lens Imaging"

Code for Lensless Learning Paper

Project page of the paper 'Deep Learning for Handling Kernel/model Uncertainty in Image Deconvolution' (CVPR 2020)

Optimizing phase mask for a lensless imaging system