MuLan: Adapting Multilingual Diffusion Models for 110+ Languages (无需额外训练为任意扩散模型支持多语言能力)

📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.

Mini-DALLE3: Interactive Text to Image by Prompting Large Language Models

Blind Super-Resolution of Single Remotely Sensed Hyperspectral Image, IEEE TGSR (2023)

Official code repository for ∇-Prox: Differentiable Proximal Algorithm Modeling for Large-Scale Optimization (SIGGRAPH TOG 2023)

Bidirectional 3D Quasi-Recurrent Neural Network for Hyperspectral Image Super-Resolution, J-STARS (2021).

Joint Spatial-Spectral Pattern Optimization and Hyperspectral Image Reconstruction, IEEE-JSTSP (2022).

Official Implementation of "Denoising Diffusion Semantic Segmentation with Mask Prior Modeling"

Personal toolkit

Unofficial Implementation of DragGAN - "Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold" （DragGAN 全功能实现，在线Demo，本地部署试用，代码、模型已全部开源，支持Windows, macOS, Linux）

Generate image from anything with ImageBind and Stable Diffusion

Hybrid Spectral Denoising Transformer with Guided Attention (ICCV 2023)

Mixed Attention Network for Hyperspectral Image Denoising

Hyperspectral Image Super Resolution with Real Unaligned RGB Guidance (TNNLS 2023)

Collections of different types of diffusion models on a number of toy dataset.

MulimgViewer is a multi-image viewer that can open multiple images in one interface, which is convenient for image comparison and image stitching.

This app demonstrates the controls available in WinUI and the Fluent Design System.

PyTorch implementation of "Deep Plug-and-Play Prior for Hyperspectral Image Restoration" (Neurocomputing 2022)

A blind hyperspectral reconstruction technique termed hyperspectral demosaicing (Hy-demosaicing) exploiting spectral low-rankness and spatial correlation of hyperspectral images.

Graph and Rank Regularized Matrix Recovery for Snapshot Spectral Image Demosaicing

This repository contains some utilities for deep learning project, e.g., paper writing, open source.

Torchlight is a light-weight PyTorch wrapper with many useful util functions for fast prototyping of computer vision models.

Model for the manuscript named "Spectral Response Function Guided Deep Optimization-driven Network for Spectral Super-resolution" pbulished on TNNLS

PyTorch code for our paper "Image Super-Resolution with Non-Local Sparse Attention" (CVPR2021).

game: five in a row

A Simple Stopwatch App for macOS.

The Yan Programming Language

Predict prosody labels for Chinese sentences.