Automatically erase objects in the video, such as logo, text, etc.

Overview

Video-Auto-Wipe

Read English Introduction:Here

  本人不定期的基于生成技术制作一些好玩有趣的算法模型,这次带来的作品是“视频擦除”方向的应用模型,它实现的功能是自动感知到视频中我们不想看见的部分(譬如广告、水印、字幕、图标等等)然后进行擦除。由于图标擦除模型存在潜在的被利用于侵权行为的隐患,因此我暂时只分享了字幕擦除模型,希望能帮助到大家。
  我后续会持续不断的探索和制作新的生成方向的技术内容。基于生成模型可玩的点还有很多,此项目仅展示了其中一个做落地应用的例子。本项目的模型版权所属为:www.seeprettyface.com ,未获得授权请不要直接用作商业用途。关于算法的细节介绍可以参阅我的研究笔记



效果预览

1. 图标擦除

  图标擦除模型的功能是模型自动感知到视频中图标的位置然后进行擦除,感知图标的方法为在时域上静止不动的小块像素块被视作图标。

1.1 测试1-电视剧的台标、剧名和角标擦除

Image text

查看视频



1.2 测试2-足球赛的台标、状态栏擦除

Image text

查看视频



1.3 测试3-综艺节目的台标、状态栏擦除

Image text

查看视频



1.4 测试4-短视频MV的遮挡图标擦除

Image text

查看视频



1.5 测试5-短视频MV的遮挡水印擦除

Image text

查看视频



1.6 测试6-新闻媒体的台标擦除

Image text

查看视频





2. 动态图标擦除

  动态图标擦除模型的功能是模型自动感知到视频中动态图标的位置然后进行擦除,感知动态图标的方法为在时域上闪烁出现或动态移动的固定像素块被视作动态图标,这个在制作上有一定难度所以还没有对外开放。

2.1 测试1-闪烁出现的特效文字擦除

Image text

Image text

查看视频





3. 字幕擦除

  字幕擦除模型的功能是模型自动感知到视频中字幕的位置然后进行擦除,感知字幕的方法为具有统一样式的文字区域被视作字幕。

3.1 测试1-电影字幕擦除

Image text

查看视频



3.2 测试2-电视剧字幕擦除

Image text

查看视频



3.3 测试3-综艺节目字幕擦除

Image text

查看视频



3.4 测试4-综艺节目特殊字幕擦除

Image text

查看视频



3.5 测试5-网络视频字幕擦除

Image text

查看视频



3.6 测试6-小语种字幕擦除

Image text

查看视频





使用方法

1.环境配置

  torch>1.0
  其他的缺什么依赖就pip install xxx,需要的东西不多

2.运行方法

  1. 下载预训练模型放在pretrained-weight文件夹里;
    预训练模型下载地址:链接:https://pan.baidu.com/s/1ubZHkgkcskS7Bpg8ZbtoRQ 提取码:ricn

  2. 将视频文件和mask文件放在input文件夹里,编辑demo.py(或通过命令行参数)选中对应文件位置;
    输入样例下载地址:https://pan.baidu.com/s/1rfdAwxomCVjTJ1zwl7hu3g 提取码:qk64

  3. 图标擦除任务运行:python demo.py delogo
   字幕擦除任务运行:python demo.py detext



训练方法

训练数据

  1.YoutubeVOS2018数据集;

  2.基于搜集的300余部高清电影制作了2,709部电影片段数据集;
    下载地址:https://pan.baidu.com/s/1CIgJmFmx5iR2JfgAyjVaeg 提取码:xb7o

  3.基于搜集的40余部综艺节目制作了864部综艺片段数据集;
    下载地址:https://pan.baidu.com/s/1lJk6IIWlwxknAie0LlGYOg 提取码:9rd4

训练过程

  第1步. 针对特定任务的时域感知训练;
  第2步. 融合擦除模型的微调训练。

训练配置

最近寻觅到了一种非常简易的制作和训练方法:
  '图标擦除'模型在单卡3090上训练3天;
  '字幕擦除'模型在单卡3090上训练2天;





更多玩法

  这个项目目前还只是做了很短期的尝试,实际上视频擦除可玩的点还有很多,譬如敏感内容(涉黄涉暴等)擦除、广告擦除、指定人/物擦除、背景人擦除等等。只要是能寻找到有像素预测的场景+有像素预测的需求都是“视频擦除”可以玩出花样的情景~

Sample





了解更多

  本人的研究方向是生成模型的应用技术研究。生成技术解决的问题是像素的预测,也就是在一个有缺失/完全缺失的图像棋盘上进行像素的填补/预测,使填补/预测完的图像符合真实图像的规律。基于这种模式可展开的玩法有很多,除了我之前做的数字人生成、视频内容生成等,我们还可以拓展出更多并行的思路出来。
  尽管目前大部分的CV落地项目都集中在感知和识别任务上,而对于重构和生成任务的研发相对较少,但这不应影响我们对于生成技术价值的判断,毕竟生成技术是相对较新、参与人较少,但是应用前景较广的研究方向。我后续将持续致力于探索生成方向的落地型算法研发,欢迎访问我的网站了解这方面最新的研究进展:www.seeprettyface.com

Sample

Owner
seeprettyface.com
seeprettyface.com
Very deep VAEs in JAX/Flax

Very Deep VAEs in JAX/Flax Implementation of the experiments in the paper Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on I

Jamie Townsend 42 Dec 12, 2022
Practical tutorials and labs for TensorFlow used by Nvidia, FFN, CNN, RNN, Kaggle, AE

TensorFlow Tutorial - used by Nvidia Learn TensorFlow from scratch by examples and visualizations with interactive jupyter notebooks. Learn to compete

Alexander R Johansen 1.9k Dec 19, 2022
GradAttack is a Python library for easy evaluation of privacy risks in public gradients in Federated Learning

GradAttack is a Python library for easy evaluation of privacy risks in public gradients in Federated Learning, as well as corresponding mitigation strategies.

129 Dec 30, 2022
Code for the paper Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations (AKBC 2021).

Relation Prediction as an Auxiliary Training Objective for Knowledge Base Completion This repo provides the code for the paper Relation Prediction as

Facebook Research 85 Jan 02, 2023
Leaf: Multiple-Choice Question Generation

Leaf: Multiple-Choice Question Generation Easy to use and understand multiple-choice question generation algorithm using T5 Transformers. The applicat

Kristiyan Vachev 62 Dec 20, 2022
MOOSE (Multi-organ objective segmentation) a data-centric AI solution that generates multilabel organ segmentations to facilitate systemic TB whole-person research

MOOSE (Multi-organ objective segmentation) a data-centric AI solution that generates multilabel organ segmentations to facilitate systemic TB whole-person research.The pipeline is based on nn-UNet an

QIMP team 30 Jan 01, 2023
FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

Detectron is deprecated. Please see detectron2, a ground-up rewrite of Detectron in PyTorch. Detectron Detectron is Facebook AI Research's software sy

Facebook Research 25.5k Jan 07, 2023
L-Verse: Bidirectional Generation Between Image and Text

Far beyond learning long-range interactions of natural language, transformers are becoming the de-facto standard for many vision tasks with their power and scalabilty

Kim, Taehoon 102 Dec 21, 2022
Flexible time series feature extraction & processing

tsflex is a toolkit for flexible time series processing & feature extraction, that is efficient and makes few assumptions about sequence data. Useful

PreDiCT.IDLab 206 Dec 28, 2022
Official codebase for "B-Pref: Benchmarking Preference-BasedReinforcement Learning" contains scripts to reproduce experiments.

B-Pref Official codebase for B-Pref: Benchmarking Preference-BasedReinforcement Learning contains scripts to reproduce experiments. Install conda env

48 Dec 20, 2022
Calibrate your listeners! Robust communication-based training for pragmatic speakers. Findings of EMNLP 2021.

Calibrate your listeners! Robust communication-based training for pragmatic speakers Rose E. Wang, Julia White, Jesse Mu, Noah D. Goodman Findings of

Rose E. Wang 3 Apr 02, 2022
A lightweight face-recognition toolbox and pipeline based on tensorflow-lite

FaceIDLight 📘 Description A lightweight face-recognition toolbox and pipeline based on tensorflow-lite with MTCNN-Face-Detection and ArcFace-Face-Rec

Martin Knoche 16 Dec 07, 2022
A Real-World Benchmark for Reinforcement Learning based Recommender System

RL4RS: A Real-World Benchmark for Reinforcement Learning based Recommender System RL4RS is a real-world deep reinforcement learning recommender system

121 Dec 01, 2022
Implementation of Pooling by Sliced-Wasserstein Embedding (NeurIPS 2021)

PSWE: Pooling by Sliced-Wasserstein Embedding (NeurIPS 2021) PSWE is a permutation-invariant feature aggregation/pooling method based on sliced-Wasser

Navid Naderializadeh 3 May 06, 2022
Go from graph data to a secure and interactive visual graph app in 15 minutes. Batteries-included self-hosting of graph data apps with Streamlit, Graphistry, RAPIDS, and more!

✔️ Linux ✔️ OS X ❌ Windows (#39) Welcome to graph-app-kit Turn your graph data into a secure and interactive visual graph app in 15 minutes! Why This

Graphistry 107 Jan 02, 2023
Source code for "Taming Visually Guided Sound Generation" (Oral at the BMVC 2021)

Taming Visually Guided Sound Generation • [Project Page] • [ArXiv] • [Poster] • • Listen for the samples on our project page. Overview We propose to t

Vladimir Iashin 226 Jan 03, 2023
The code for SAG-DTA: Prediction of Drug–Target Affinity Using Self-Attention Graph Network.

SAG-DTA The code is the implementation for the paper 'SAG-DTA: Prediction of Drug–Target Affinity Using Self-Attention Graph Network'. Requirements py

Shugang Zhang 7 Aug 02, 2022
Distributionally robust neural networks for group shifts

Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization This code implements the g

151 Dec 25, 2022
[NeurIPS 2021] Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data

Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data (NeurIPS 2021) This repository will provide the official PyTorch implementa

Liming Jiang 238 Nov 25, 2022
A variational Bayesian method for similarity learning in non-rigid image registration (CVPR 2022)

A variational Bayesian method for similarity learning in non-rigid image registration We provide the source code and the trained models used in the re

daniel grzech 14 Nov 21, 2022