Style Transfer etc.

Style Transfer etc.

- 10월 20, 2017

딥러닝 기반 인스턴스 세그멘테이션:

Dai,rH, and9Sun,6“Instance-aware Semantic Segmentation via Multi-task Network Cascades”,0CVPR 2016

딥러닝 기반 포즈 에스티메이션:

Cao et al, “Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields”, arXiv 2016

이미지 캡셔닝:

Karpathy and Fei-Fei, “Deep Visual-Semantic Alignments for Generating Image Descriptions”, CVPR 2015

덴스 이미지 캡션:

Johnson, Karpathy, and Fei-Fei, “DenseCap: Fully Convolutional Localization Networks for Dense Captioning”, CVPR 201

이미지 퀘스쳔:

Agrawal et al, “VQA: Visual Question Answering”, ICCV 2015

슈퍼 레졸루션:

Ledig et al, “Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network”, arXiv 2016

이미지 스타일 트랜스퍼:

Gatys, Ecker, and Bethge, “Image StyleTransfer using Convolutional Neural Networks”, CVPR 201

가이디드 백프로파게이션:

Dosovitskiy et al, “Striving for Simplicity: The AllConvolutional Net”, ICLR Workshop 2015

Dosovitskiy et al, “Striving for Simplicity: The All Convolutional Net”, ICLR Workshop

그래디언트 어센트:

Simonyan et al, “Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps”

피쳐 인버죤:

Mahendran and Vedaldi, “Understanding Deep Image Representations by Inverting Them”, CVPR 2015

텍스쳐 신세시스:

Gatys et al, “Texture Synthesis using Convolutional Neural Networks”, NIPS 2015

뉴럴 스타일:

Justin Johnson, “neural-style”, https://github.com/jcjohnson/neural-style

컬러보존 뉴럴스타일:

Gatys et al, “Preserving Color in Neural Artistic Style Transfer”, arXiv 2016

비디오 뉴럴스타일:

Ruder et al, “Artistic style transfer for videos”, arXiv 2016

CNNMRF:

Li and Wand, “Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis”, CVPR 2016

Fast neuralstyle:

Johnson et al, “Perceptual Losses for Real-Time Style Transfer and Super-Resolution”, ECCV 2016

Texture Network:

Ulyanov et al, “Texture Networks: Feed-forward Synthesis of Textures and Stylized Images”, ICML 2016

Instance Normalization:

Ulyanov et al, “Instance Normalization: The Missing Ingredient for Fast Stylization”, ICML 2016

댓글