S-aiueo32

DeqIR

PyTorch implementation of "Deep Equilibrium Diffusion Restoration with Parallel Sampling (CVPR 2024)"

ESTextSpotter

(ICCV 2023) ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer

efficient-kan

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

pykan

Kolmogorov Arnold Networks

extension-cpp

C++ extensions in PyTorch

Monkey

【CVPR 2024 Highlight】Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models

awesome-document-understanding

A curated list of resources for Document Understanding (DU) topic

CCSR

Official codes of CCSR: Improving the Stability of Diffusion Models for Content Consistent Super-Resolution

SwinTextSpotter

Pytorch re-implementation of Paper: SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition (CVPR 2022)

Bridging-Text-Spotting

(CVPR 2024) Bridging the Gap Between End-to-End and Two-Step Text Spotting.

torchdynamo

A Python-level JIT compiler designed to make unmodified PyTorch programs faster.

manga-image-translator

Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/

llama3

The official Meta Llama 3 GitHub site

AddSR

DPText-DETR

[AAAI'23 Oral] DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer

schedule_free

Schedule-Free Optimization in PyTorch

large-ocr-model.github.io

tao_pytorch_backend

TAO Toolkit deep learning networks with PyTorch backend

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

doc3D-dataset

A hybrid dataset for document unwarping (Paper: https://www3.cs.stonybrook.edu/~cvl/projects/dewarpnet/storage/paper.pdf)

grok-1

Grok open release

GiT

Official Implementation of "GiT: Towards Generalist Vision Transformer through Universal Language Interface"

desigen

Official code for paper: Desigen: A Pipeline for Controllable Design Template Generation [CVPR'24]

deepdoctection

A Repo For Document AI

SPTSv2

The official implementation of SPTS v2: Single-Point Text Spotting

calibration-framework

The net:cal calibration framework is a Python 3 library for measuring and mitigating miscalibration of uncertainty estimates, e.g., by a neural network.

manim

Animation engine for explanatory math videos

vscode-extension-samples

Sample code illustrating the VS Code extension API.

VIPTR

WGSR