ewrfcas

Face-Super-Resolution

Face super resolution based on ESRGAN

bert_cn_finetune

Bert finetune for CMRC2018, CJRC, DRCD, CHID, C3

MVSFormer

Codes of MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depth (TMLR2023)

MST_inpainting

Learning a Sketch Tensor Space for Image Inpainting of Man-made Scenes (ICCV 2021)

MAE-FAR

Codes of Learning Prior Feature and Attention Enhanced Image Inpainting (ECCV2022)

LeftRefill

LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model (CVPR2024)

ZITS-PlusPlus

ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priors (TPAMI2023)

CasMTR

Official codes of Improving Transformer-based Image Matching by Cascaded Capturing Spatially Informative Keypoints (ICCV2023)

face_attribute_classification_pytorch

face attribute classification based on pytorch

Pixel2MeshPlusPlus-MVDISN

Pixel2Mesh++: 3D Mesh Generation and Refinement from Multi-View Images (TPAMI2022)

DocRED_Bert

A bert baseline for DocRED

iLAT

The Image Local Autoregressive Transformer (NIPS2021)

TSDF_pytorch

TSDF（Truncated Signed Distance Function）in pytorch

LightHanlp2_pytorch

基于pytorch的轻量级hanlp2.0工具，支持中文分词，词性分类，实体抽取，句法分析，语义分析

StructureUpsampling

Simple CNN for line and edge upsampling.

tensorflow_recompute

tensorflow recompute demo

ewrfcas.github.io

Policy-Gradient-NLP

Some samples of policy gradient used in Chinese NLP tasks (Machine reading comprehension, text shuffle).

umamusume_reinforcement_policy

ウマ娘 プリティーダービー!

Anime_Rec

Anime recommendation with reviews

daily_fudan

一键平安复旦小脚本，自动化快速上报疫情

ewrfcas

Hifill-tensorflow

Tensorflow reimplementation of Hifill

Inpainting-Structural-Explorer

This project only contains ablation studies for ONE-STAGE inpainting models

MasterDuelSimpleTranslateTool

MasterDuelTranslate(Use Ygo Card DataBase,belong win32 window shot & image match)

mipnerf

openMVS

open Multi-View Stereo reconstruction library

pix2pixHD

Synthesizing and manipulating 2048x1024 images with conditional GANs

Pixel2MeshPlusPlus

Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation. In ICCV2019.

white-paper

Simple, elegant and clean jekyll theme.