[zz] 2018 CVPR GAN 相關論文調研
風格遷移
1. PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup
(給人臉化妝的風格轉移)
2.CartoonGAN: Generative Adversarial Networks for Photo Cartoonization
(將圖片轉化為卡通風格的GAN)
3.StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
(人臉多種風格轉換)
4.Multi-Content GAN for Few-Shot Font Style Transfer
(字型風格轉換)
5.DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks
(圖到圖轉換)
6. Conditional Image-to-Image translation
(圖到圖的轉換)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Lin_Conditional_Image-to-Image_Translation_CVPR_2018_paper.pdf
圖片處理
1. DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks
(去模糊)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Kupyn_DeblurGAN_Blind_Motion_CVPR_2018_paper.pdf
2.Attentive Generative Adversarial Network for Raindrop Removal from A Single Image
(去除圖片中的雨滴)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Qian_Attentive_Generative_Adversarial_CVPR_2018_paper.pdf
3. Deep Photo Enhancer: Unpaired Learning for Image Enhancement from Photographs with GANs
(用於照片增強)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_Deep_Photo_Enhancer_CVPR_2018_paper.pdf
4. SeGAN: Segmenting and Generating the Invisible
(去遮擋)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Ehsani_SeGAN_Segmenting_and_CVPR_2018_paper.pdf
5.Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal
(去陰影)
6.Image Blind Denoising With Generative Adversarial Network Based Noise Modeling
(去噪聲)
7. Single Image Dehazing via Conditional Generative Adversarial Network
(去噪聲)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Single_Image_Dehazing_CVPR_2018_paper.pdf
圖片生成
1. ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing
(空間轉換生成圖片)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Lin_ST-GAN_Spatial_Transformer_CVPR_2018_paper.pdf
2. SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis
(由邊框生成圖片)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_SketchyGAN_Towards_Diverse_CVPR_2018_paper.pdf
3. TextureGAN: Controlling Deep Image Synthesis with Texture Patches
(由紋路生成圖片)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Xian_TextureGAN_Controlling_Deep_CVPR_2018_paper.pdf
4. Eye In-Painting with Exemplar Generative Adversarial Networks
(給人物畫眼睛)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Dolhansky_Eye_In-Painting_With_CVPR_2018_paper.pdf
5.Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network
(文字生成圖片)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Photographic_Text-to-Image_Synthesis_CVPR_2018_paper.pdf
6. Logo Synthesis and Manipulation with Clustered Generative Adversarial Networks
(生成logo)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Sage_Logo_Synthesis_and_CVPR_2018_paper.pdf
7. Cross-View Image Synthesis Using Conditional GANs
(街區俯檢視和直視轉換)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Regmi_Cross-View_Image_Synthesis_CVPR_2018_paper.pdf
8. AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
(文字生成圖片)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Xu_AttnGAN_Fine-Grained_Text_CVPR_2018_paper.pdf
9. High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
(影象高解析度)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_High-Resolution_Image_Synthesis_CVPR_2018_paper.pdf
人臉相關
1. Finding Tiny Faces in the Wild with Generative Adversarial Network
(對低解析度的人臉檢測)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Bai_Finding_Tiny_Faces_CVPR_2018_paper.pdf
2. Learning Face Age Progression: A Pyramid Architecture of GANs
(預測年齡)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Yang_Learning_Face_Age_CVPR_2018_paper.pdf
3. Super-FAN: Integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs
(對低解析度人臉超解析度)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Bulat_Super-FAN_Integrated_Facial_CVPR_2018_paper.pdf
(人臉合成)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Bao_Towards_Open-Set_Identity_CVPR_2018_paper.pdf
5. Weakly Supervised Facial Action Unit Recognition through Adversarial Training
(人臉表情識別)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Peng_Weakly_Supervised_Facial_CVPR_2018_paper.pdf
6.FaceID-GAN: Learning a Symmetry Three-Player GAN for Identity-Preserving Face Synthesis
(生成多角度人臉)
7. UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition
(人臉生成)
8.Face Aging with Identity-Preserved Conditional Generative Adversarial Networks
(人臉老化)
人體相關
1. Deformable GANs for Pose-based Human Image Generation
(人物姿態遷移)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Siarohin_Deformable_GANs_for_CVPR_2018_paper.pdf
2. Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks
(用GAN生成人行為軌跡追蹤)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Gupta_Social_GAN_Socially_CVPR_2018_paper.pdf
3. GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB
(用GAN生成的手勢圖片做手勢追蹤的資料集)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Mueller_GANerated_Hands_for_CVPR_2018_paper.pdf
4. Multistage Adversarial Losses for Pose-Based Human Image Synthesis
(人體姿態合成)
5. Disentangled Person Image Generation
(人體合成)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Ma_Disentangled_Person_Image_CVPR_2018_paper.pdf
domain adaptation
(這個沒來得及找了,可能轉行咯~ 唉)
1. Generate to Adapt: Aligning Domains Using Generative Adversarial Networks
2. Re-Weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation
3. Adversarial Feature Augmentation for Unsupervised Domain Adaptation
4. Domain Generalization With Adversarial Feature Learning
5. Image to Image Translation for Domain Adaptation
6. Duplex Generative Adversarial Network for Unsupervised Domain Adaptation
7. Conditional Generative Adversarial Network for Structured Domain Adaptation
目標跟蹤檢測
1.Generative Adversarial Learning Towards Fast Weakly Supervised Detection
(弱監督檢測)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Shen_Generative_Adversarial_Learning_CVPR_2018_paper.pdf
2. SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation
(對抗學習生成軌跡樣本)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_SINT_Robust_Visual_CVPR_2018_paper.pdf
3. VITAL: VIsual Tracking via Adversarial Learning
http://openaccess.thecvf.com/content_cvpr_2018/papers/Song_VITAL_VIsual_Tracking_CVPR_2018_paper.pdf
GAN模型優化
1. SGAN: An Alternative Training of Generative Adversarial Network
(替代訓練GAN)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Chavdarova_SGAN_An_Alternative_CVPR_2018_paper.pdf
2. GAGAN: Geometry-Aware Generative Adversarial Networks
(一種關注幾何外形的GAN)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Kossaifi_GAGAN_Geometry-Aware_Generative_CVPR_2018_paper.pdf
3.Global versus Localized Generative Adversarial Nets
(區域性優化GAN)
4. Generative Adversarial Image Synthesis with Decision Tree Latent Controller
(決策樹)
5. Unsupervised Deep Generative Adversarial Hashing Network
(雜湊GAN)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Dizaji_Unsupervised_Deep_Generative_CVPR_2018_paper.pdf
6. Multi-Agent Diverse Generative Adversarial Networks
(多個生成器GAN)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Ghosh_Multi-Agent_Diverse_Generative_CVPR_2018_paper.pdf
7. Duplex Generative Adversarial Network for Unsupervised Domain Adaptation
(雙鑑別器GAN)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Hu_Duplex_Generative_Adversarial_CVPR_2018_paper.pdf
影象分割
1. Translating and Segmenting Multimodal Medical Volumes With Cycle- and Shape-Consistency Generative Adversarial Network
(影象分割)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Translating_and_Segmenting_CVPR_2018_paper.pdf
行人重識別
1. Person Transfer GAN to Bridge Domain Gap for Person Re-Identification
(用GAN生成的人體檢測的圖片)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Wei_Person_Transfer_GAN_CVPR_2018_paper.pdf
2. Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
http://openaccess.thecvf.com/content_cvpr_2018/papers/Deng_Image-Image_Domain_Adaptation_CVPR_2018_paper.pdf
視覺特徵提取
1. Visual Feature Attribution using Wasserstein GANs
http://openaccess.thecvf.com/content_cvpr_2018/papers/Baumgartner_Visual_Feature_Attribution_CVPR_2018_paper.pdf
域自適應學習
1. Generate To Adapt: Aligning Domains using Generative Adversarial Networks
(視覺域自適應)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Sankaranarayanan_Generate_to_Adapt_CVPR_2018_paper.pdf
影象檢索
1. HashGAN: Deep Learning to Hash with Pair Conditional Wasserstein GAN
http://openaccess.thecvf.com/content_cvpr_2018/papers/Cao_HashGAN_Deep_Learning_CVPR_2018_paper.pdf
遷移學習
1.Partial Transfer Learning With Selective Adversarial Networks
http://openaccess.thecvf.com/content_cvpr_2018/papers/Cao_Partial_Transfer_Learning_CVPR_2018_paper.pdf
視訊生成
1. MoCoGAN: Decomposing Motion and Content for Video Generation
(用GAN生成視訊)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Tulyakov_MoCoGAN_Decomposing_Motion_CVPR_2018_paper.pdf
2. Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks
(生成延時視訊)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Xiong_Learning_to_Generate_CVPR_2018_paper.pdf
小結:
可以看出GAN相關的論文還不少呀,各個方面的都有,可是我個人覺得,可能沒有那種特別厲害的吧~hh
--------------------- 本文來自 眉間細雪 的CSDN 部落格 ,全文地址請點選:https://blog.csdn.net/weixin_42445501/article/details/82792311?utm_source=copy相關推薦
[zz] 2018 CVPR GAN 相關論文調研
風格遷移 1. PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup (給人臉化妝的風格轉移) 2.CartoonGAN: Generative Adversarial Networks f
2018 CVPR GAN 相關論文調研 (自己分了下類,附地址哦)
2018 CVPR GAN 相關論文調研 風格遷移 1. PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup (給人臉化妝的風格轉移) http://openaccess.thecvf.com/
CVPR 2018遷移學習相關論文
使用語義保持對抗嵌入網路的零樣本視覺識別 摘要:我們提出了一種新的框架,稱為語義保持對抗嵌入網路(SP-AEN),用於零樣本視覺識別(ZSL),其中測試影象及其類別在訓練期間都是不可見的。 SP-AEN旨在解決流行的基於嵌入的ZSL系列中的固有問題 - 語
CVPR 2018 目標跟蹤相關論文
這裡列出列表,每篇論文會單獨寫一篇部落格。 《Multi-Cue Correlation Filters for Roubust Visual Tracking》 《Learning Attentions: Residual Attentional Siamese Net
CVPR 2018 paper list(論文列表)
52 Embodied Question Answering Abhishek Das (Georgia Tech); Samyak Datta (Georgia Tech); Georgia Gkioxari (Facebook); Stefan
cvpr 2018 image caption generation論文導讀(含workshop)
這是之前的一篇部落格,關於影象描述(image caption)的一些看法,現在看來,當時的看法有正確的,也有很多地方有點淺薄,僅供交流,下面是2018cvpr關於這個方向的論文,看看大牛們都是怎麼搞這個方向的。 當時說的第一點,評價現在的確有人用深度開始做了
sketch 相關論文
tran finall ddr simple ger sent ref dom sta sketch 相關論文 Sketch Simplification We present a novel technique to simplify sketch drawings b
深度學習相關論文
1. 深度學習基礎及歷史 1.0 書 [0] 深度學習聖經 ★★★★★ Bengio, Yoshua, Ian J. Goodfellow, and AaronCourville. "Deep learning." An MIT Press book. (2015). https:/
NLP之WE之CBOW&Skip-Gram:CBOW&Skip-Gram演算法概念相關論文、原理配圖、關鍵步驟詳細攻略
NLP之WE之CBOW&Skip-Gram:CBOW&Skip-Gram演算法相關論文、原理配圖、關鍵步驟詳細攻略 CBOW&Skip-Gram演算法相關論文 CBOW 模型和Skip-Gram 模型,參考論文《Efficient Estimation of Wo
FE之DR之線性降維:LDA&PCA演算法相關論文、主要思路、關鍵步驟、程式碼實現等相關配圖之詳細攻略
FE之DR之LDA:LDA演算法相關論文、主要思路、關鍵步驟、程式碼實現等相關配圖之詳細攻略 LDA LDA演算法相關論文、主要思路 1、LDA的缺點:強依賴均值。以下是LDA搞不定的四種情況 LDA演算法關鍵步驟 1、LDA演算法推導 &n
CVPR 2017部分論文小結
語義分割與物體識別 One-Shot Video Object Segmentation 本文處理了視訊物體分割的問題。 本文提出模型OSVOS,利用第一幀標註的圖片來實現整個視訊序列中該物體的分割。所有幀都均為獨立處理,但結果卻很穩定連貫,並達到state-of-the-art。
ML之Clustering之普聚類演算法:普聚類演算法的相關論文、主要思路、關鍵步驟、程式碼實現等相關配圖之詳細攻略
ML之Clustering之普聚類演算法:普聚類演算法的相關論文、主要思路、關鍵步驟、程式碼實現等相關配圖之詳細攻略 普聚類演算法的相關論文 1、論文推薦 Clustering by fast search and find of density peak.
SDN網路虛擬化、資源對映等相關論文粗讀
1. 用SDN網路管理器控制平面延遲:虛擬化的代價 基本結構:虛擬機器監控程式位於多個虛擬SDN網路和租戶控制器之間,其中的虛擬SDN網路位於底層的物理SDN網路基礎結構上。 NV:網路虛擬化,和SDN結合,可以建立虛擬SDN網路,租戶可以通過開放的網路介面和協議程式設計他們的vSDN資源,並執行屬於他們自
如何查詢NLP相關論文
如何檢索自然語言處理領域相關論文 前言 針對自身的情況,發現個人查詢論文的能力,看論文的能力有些薄弱。特此進行如果檢索合適的論文寫一個部落格。 本文主要是摘自劉知遠 老師的新浪部落格和南京理工大學文字挖掘研究組部落格 綜述 要快速地熟悉一個領域,更加深刻地瞭
RGB-D 稠密slam相關論文整理
綜合方向梳理 瞭解一下RGB-D SLAM中各開原始碼的效能對比以及所使用方法的異同。 Davison實驗室套餐 Elastic Fusion: DynamicFusion Dynamic
GAN相關資源
AdversarialNetsPapers The classical Papers about adversarial nets The First paper ✅ [Generative Adversarial Nets] [Paper] [Code](the fi
學習筆記2018-10-26 讀論文A single algorithm to retrieve turbidity from remotely-sensed data in all coastal
TOPIC: A single algorithm to retrieve turbidity from remotely-sensed data in all coastal and estuarine waters from RSE WRITERS: A.I
BERT相關論文、文章和程式碼資源彙總
摘自 我愛自然語言處理 BERT相關論文、文章和程式碼資源彙總 BERT最近太火,蹭個熱點,整理一下相關的資源,包括Paper, 程式碼和文章解讀。 1、Google官方: 1) BERT: Pre-training of Deep Bidirecti
IPv6 相關技術調研
最近,需要對系統進行 IPv6 化的改造,於是,我就假模假樣的做起了調研。 IPv6 的表示方法 IPv6 地址為 128 位長,但通常寫作 8 組,每組為四個十六進位制數的形式。例如: 2001:0db8:85a3:08d3:1319:8a2e:0370:7344 如
EMNLP2018 | 騰訊AI Lab深度解讀文字生成技術相關論文
感謝閱讀騰訊AI Lab微訊號第49篇文章。NLP領域三大頂會之一的EMNLP即將舉辦,騰訊AI