diff --git a/README.md b/README.md index 9a63e45..e8214ce 100644 --- a/README.md +++ b/README.md @@ -8,6 +8,7 @@ __Note: General GAN papers targeting simple image generation such as DCGAN, BEGA ## The landmark papers that I respect. + Generative Adversarial Networks, [[paper]](https://arxiv.org/abs/1406.2661), [[github]](https://github.com/goodfeli/adversarial) + Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, [[paper]](https://arxiv.org/pdf/1511.06434), [[github]](https://github.com/soumith/dcgan.torch) ++ Improved Techniques for Training GANs, [[paper]](https://arxiv.org/pdf/1606.03498.pdf), [[github]](https://github.com/openai/improved-gan) + BEGAN: Boundary Equilibrium Generative Adversarial Networks, [[paper]](https://arxiv.org/pdf/1703.10717), [[github]](https://github.com/carpedm20/BEGAN-tensorflow) ----- @@ -29,12 +30,14 @@ __Use this contents list or simply press command + F to se + [High-resolution image generation (large-scale image)](#high-resolution-image-generation-large-scale-image) + [Adversarial Examples (Defense vs Attack)](#adversarial-examples-defense-vs-attack) + [Visual Saliency Prediction (attention prediction)](#visual-saliency-prediction-attention-prediction) + + [Object Detection/Recognition](#object-detectionrecognition) + [Did not use GAN, but still interesting applications](#did-not-use-gan-but-still-interesting-applications) + + [Real-time face reconstruction](#real-time-face-reconstruction) + [Super-resolution](#super-resolution-1) - + [Photorealistic Image geneation (e.g. pix2pix, sketch2image)](#photorealistic-image-geneation-eg-pix2pix-sketch2image) + + [Photorealistic Image generation (e.g. pix2pix, sketch2image)](#photorealistic-image-generation-eg-pix2pix-sketch2image) + [Human Pose Estimation](#human-pose-estimation-1) - + [3D Obejct generation](#3d-obejct-generation-1) + + [3D Object generation](#3d-object-generation-1) + [GAN tutorials with easy and simple example code for starters](#gan-tutorials-with-easy-and-simple-example-code-for-starters) + [Implementations of various types of GANs collection](#implementations-of-various-types-of-gans-collection) @@ -63,7 +66,7 @@ __Use this contents list or simply press command + F to se + Generative Adversarial Text to Image Synthesis, [[paper]](https://arxiv.org/pdf/1605.05396.pdf), [[github]](https://github.com/paarthneekhara/text-to-image), [[github]](https://github.com/reedscot/icml2016) + Learning What and Where to Draw, [[paper]](http://www.scottreed.info/files/nips2016.pdf), [[github]](https://github.com/reedscot/nips2016) -### 3D Obejct generation +### 3D Object generation + Parametric 3D Exploration with Stacked Adversarial Networks, [[github]](https://github.com/maxorange/pix2vox), [[youtube]](https://www.youtube.com/watch?v=ITATOXVvWEM) + Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling, [[paper]](http://papers.nips.cc/paper/6096-learning-a-probabilistic-latent-space-of-object-shapes-via-3d-generative-adversarial-modeling.pdf), [[github]](https://github.com/zck119/3dgan-release), [[youtube]](https://www.youtube.com/watch?v=HO1LYJb818Q) @@ -123,18 +126,33 @@ Shapes via 3D Generative-Adversarial Modeling, [[paper]](http://papers.nips.cc/p + Perceptual Generative Adversarial Networks for Small Object Detection, [[paper]](https://arxiv.org/pdf/1706.05274) + Adversarial Generation of Training Examples for Vehicle License Plate Recognition, [[paper]](https://arxiv.org/pdf/1707.03124.pdf) +### Robotics ++ Unsupervised Pixel–Level Domain Adaptation with Generative Adversarial Networks, [[paper]](https://arxiv.org/pdf/1612.05424.pdf), [[github]](https://github.com/rhythm92/Unsupervised-Pixel-Level-Domain-Adaptation-with-GAN) + +### Video (generation/prediction) ++ DEEP MULTI-SCALE VIDEO PREDICTION BEYOND MEAN SQUARE ERROR, [[paper]](https://arxiv.org/pdf/1511.05440.pdf), [[github]](https://github.com/dyelax/Adversarial_Video_Generation) + +### Synthetic Data Generation ++ Learning from Simulated and Unsupervised Images through Adversarial Training, [[paper]](https://arxiv.org/pdf/1612.07828.pdf), [[github]](https://github.com/carpedm20/simulated-unsupervised-tensorflow) + +### Others ++ (Physics) Learning Particle Physics by Example: +Location-Aware Generative Adversarial Networks for +Physics Synthesis, [[paper]](https://arxiv.org/pdf/1701.05927.pdf), [[github]](https://github.com/hep-lbdl/adversarial-jets) + + ----- ## Did not use GAN, but still interesting applications. ### Real-time face reconstruction -+ Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction, [[paper]](https://arxiv.org/pdf/1703.10580.pdf), [[github]](), [[youtube]](https://www.youtube.com/watch?v=uIMpHZYB8fI) ++ Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction, [[paper]](https://arxiv.org/pdf/1703.10580.pdf), [[github]](https://github.com/waxz/MoFA), [[youtube]](https://www.youtube.com/watch?v=uIMpHZYB8fI) ### Super-resolution + Learning to Simplify: Fully Convolutional Networks for Rough Sketch Cleanup, [[paper]](http://delivery.acm.org/10.1145/2930000/2925972/a121-simo-serra.pdf?ip=111.91.137.238&id=2925972&acc=ACTIVE%20SERVICE&key=58C7DD92F91E3631%2E58C7DD92F91E3631%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&CFID=818332500&CFTOKEN=94661101&__acm__=1507786813_0e5b28dfb97e654d0126d61b0aa592f4), [[site link]](http://hi.cs.waseda.ac.jp/~esimo/en/research/sketch/), [[youtube]](https://www.youtube.com/watch?v=4MfG9CDufPA) -### Photorealistic Image geneation (e.g. pix2pix, sketch2image) +### Photorealistic Image generation (e.g. pix2pix, sketch2image) + The Sketchy Database: Learning to Retrieve Badly Drawn Bunnies, [[paper]](http://delivery.acm.org/10.1145/2930000/2925954/a119-sangkloy.pdf?ip=111.91.137.238&id=2925954&acc=CHORUS&key=58C7DD92F91E3631%2E58C7DD92F91E3631%2E4D4702B0C3E38B35%2E6D218144511F3437&CFID=818332500&CFTOKEN=94661101&__acm__=1507787415_cb950c300370fc27da68920a0d5b5178), [[youtube]](https://www.youtube.com/watch?v=a3sgFQjEfp4) + PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing, [[paper]](https://www.researchgate.net/profile/Eli_Shechtman/publication/220184392_PatchMatch_A_Randomized_Correspondence_Algorithm_for_Structural_Image_Editing/links/02e7e520897b12bf0f000000.pdf), [[github]](https://github.com/younesse-cv/PatchMatch), [[youtube]](https://www.youtube.com/watch?v=n3aoc36V8LM) @@ -161,6 +179,14 @@ Fully Convolutional Networks for Rough Sketch Cleanup, [[paper]](http://delivery + [wiseodd/generative-models](https://github.com/wiseodd/generative-models), both pytorch and tensorflow +___ + +## Trendy AI-application Articles ++ [Artificial intelligence can say yes to the dress](https://qz.com/1090267/artificial-intelligence-can-now-show-you-how-those-pants-will-fit/) + + + + ## Author Minchul Shin, [@nashory](https://github.com/nashory)