upsampling 开源项目推荐（110 个）

bloc97 /Anime4K

用于动漫视频的高质量实时超分器

GeorgeSeif /Semantic-Segmentation-Suite

Semantic Segmentation Suite in TensorFlow. Implement, train, and test new Semantic Segmentation models easily!

EthicalML /xai

XAI——面向机器学习的可解释性工具箱

maum-ai /nuwave2

NU-Wave 2：针对不同采样率的通用神经音频上采样模型 @ INTERSPEECH 2022

maum-ai /nuwave

NU-Wave：神经音频上采样的扩散概率模型 @ INTERSPEECH 2021

mikigal /Anime4K-GUI

Anime upscaler GUI application based on Anime4K shaders which allows to save upscaled video to disk

chenmozhijin /NijiLucid

基于 WebGPU 的浏览器扩展，支持多种超分模型，实时提升动漫视频画质 | A WebGPU browser extension with multiple super-resolution models for real-time anime video enhancement.

Alexkral /AviSynthAiUpscale

部分超分辨率卷积神经网络的 AviSynth+ 实现。

preritj /segmentation

Tensorflow implementation : U-net and FCN with global convolution

GioF71 /squeezelite-docker

Easily run SqueezeLite with Alsa or PulseAudio output with Docker. Bluetooth support. Upsampling 2x 4x 8x with settings by Archimago

HolmesShuan /Location-aware-Upsampling-for-Semantic-Segmentation

The Pytorch implementation of "Location-aware Upsampling for Semantic Segmentation" (LaU)

Communist02 /AnimePlayer

Video player with the function of improving the quality of the hand-drawn image using the high-performance scaling algorithm of Anime4K

GioF71 /mpd-alsa-docker

Easily run mpd with Alsa or PulseAudio output with Docker. Upsampling 2x 4x 8x 16x with multiple soxr presets including goldilocks and extremus settings by Archimago. Scrobbling support.

pezcode /mosaiikki

Checkerboard rendering with Magnum and OpenGL

abdo-eldesokey /RAFT-NCUP

The official PyTorch implementation for "Normalized Convolution Upsampling for Refined Optical Flow Estimation"

shizenglin /Unsharp-Mask-Guided-Filtering

Code for "Unsharp Mask Guided Filtering, IEEE Transactions on Image Processing, 2021"

codebydant /upsamplingCloudPCL

Upsampling method for an input cloud using mls method of PCL

Nikait /FastWave

FastWave is a lightweight diffusion model for general audio super-resolution (any -> 48 kHz). SOTA quality reconstruction metrics with just 1.3 M parameters and ~50 GFLOPs

TianZerL /Anime4KGo

Implementation of Anime4K in Go.

GINK03 /keras-rnn-music-super-resolution

DeepLearningで音楽をアップサンプリングします