图像生成 - arXivDaily 专题

1905.11574 2020-10-22 cs.CV cs.LG 57%

JGAN: A Joint Formulation of GAN for Synthesizing Images and Labels

Minje Park

专题命中可控生成：image generation(abstract)；分类 cs.CV

Comments To be published in IEEE Access

2010.07646 2020-10-16 cs.CV cs.RO 57%

Empty Cities: a Dynamic-Object-Invariant Space for Visual SLAM

Berta Bescos, Cesar Cadena, Jose Neira

专题命中可控生成：inpainting(abstract)；分类 cs.CV

2007.01151 2020-10-15 cs.CV 57%

JUMPS: Joints Upsampling Method for Pose Sequences

Lucas Mourot, François Le Clerc, Cédric Thébault, Pierre Hellier

专题命中可控生成：inpainting(abstract)；分类 cs.CV

Comments 8 pages, 7 figures, 2 tables

2010.05655 2020-10-13 cs.GR 57%

Intuitive Facial Animation Editing Based On A Generative RNN Framework

Eloïse Berson, Catherine Soladié, Nicolas Stoiber

专题命中可控生成：inpainting(abstract)；分类 cs.GR

Journal ref Computer Graphics Forum 2020

2010.00947 2020-10-05 cs.CV 57%

MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination

Shengyu Zhang, Donghui Wang, Zhou Zhao, Siliang Tang, Di Xie, Fei Wu

专题命中可控生成：image generation(abstract)；分类 cs.CV

Comments 8 pages, 6 figures

2008.03633 2020-09-29 cs.CV eess.IV 57%

Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumes

Juan Luis Gonzalez, Munchurl Kim

专题命中可控生成：image synthesis(abstract)；分类 cs.CV

Comments Accepted to NeurIPS2020

2009.08849 2020-09-21 cs.CV 57%

Synthetic Convolutional Features for Improved Semantic Segmentation

Yang He, Bernt Schiele, Mario Fritz

专题命中可控生成：image synthesis(abstract)；分类 cs.CV

Comments ECCV 2020 Workshop on Assistive Computer Vision and Robotics

2008.04095 2020-09-14 cs.CV 57%

Fighting Deepfake by Exposing the Convolutional Traces on Images

Luca Guarnera, Oliver Giudice, Sebastiano Battiato

专题命中可控生成：image generation(abstract)；分类 cs.CV

Comments arXiv admin note: text overlap with arXiv:2004.10448

Journal ref IEEE Access 2020

2009.04065 2020-09-10 cs.CV 57%

View-consistent 4D Light Field Depth Estimation

Numair Khan, Min H. Kim, James Tompkin

专题命中可控生成：diffusion(abstract)；分类 cs.CV

Comments BMVC 2020

2003.08440 2020-09-09 cs.CV 57%

Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation

Yingda Xia, Yi Zhang, Fengze Liu, Wei Shen, Alan Yuille

专题命中可控生成：image synthesis(abstract)；分类 cs.CV

Comments ECCV 2020 Oral. The first two authors contributed equally to this work. Code available at https://github.com/YingdaXia/SynthCP

2008.10598 2020-08-25 cs.CV 57%

Semantic View Synthesis

Hsin-Ping Huang, Hung-Yu Tseng, Hsin-Ying Lee, Jia-Bin Huang

专题命中可控生成：image synthesis(abstract)；分类 cs.CV

Comments ECCV 2020. Project: https://hhsinping.github.io/svs/index.html Colab: https://colab.research.google.com/drive/1iT5PfK7zl1quAOwC227GfBjieFMVHjI5

1912.07183 2020-08-25 cs.CV 57%

MTRNet++: One-stage Mask-based Scene Text Eraser

Osman Tursun, Simon Denman, Rui Zeng, Sabesan Sivapalan, Sridha Sridharan, Clinton Fookes

专题命中可控生成：inpainting(abstract)；分类 cs.CV

Comments This paper is under CVIU review (after major revision)

2008.06048 2020-08-24 cs.SD cs.LG cs.MM 57%

MMM : Exploring Conditional Multi-Track Music Generation with the Transformer

Jeff Ens, Philippe Pasquier

专题命中可控生成：inpainting(abstract)；分类 cs.MM

2008.08145 2020-08-20 cs.CV 57%

Category Level Object Pose Estimation via Neural Analysis-by-Synthesis

Xu Chen, Zijian Dong, Jie Song, Andreas Geiger, Otmar Hilliges

专题命中可控生成：image synthesis(abstract)；分类 cs.CV

2008.04690 2020-08-12 eess.IV cs.CV 57%

Implanting Synthetic Lesions for Improving Liver Lesion Segmentation in CT Exams

Dario Augusto Borges Oliveira

专题命中可控生成：image synthesis(abstract)；分类 cs.CV

2007.12072 2020-07-28 cs.CV cs.LG eess.IV 57%

TSIT: A Simple and Versatile Framework for Image-to-Image Translation

Liming Jiang, Changxu Zhang, Mingyang Huang, Chunxiao Liu, Jianping Shi, Chen Change Loy

专题命中可控生成：image synthesis(abstract)；分类 cs.CV

Comments ECCV 2020 (Spotlight). Table 2 is updated. GitHub: https://github.com/EndlessSora/TSIT

1810.10340 2020-07-27 cs.CV cs.NE 57%

Investigating Object Compositionality in Generative Adversarial Networks

Sjoerd van Steenkiste, Karol Kurach, Jürgen Schmidhuber, Sylvain Gelly

专题命中可控生成：image generation(abstract)；分类 cs.CV

Comments A preliminary version of this work (arXiv v1) appeared under the title "A Case for Object Compositionality in Deep Generative Models of Images" as a workshop paper at the NeurIPS2018 workshop on "Modeling the Physical World: Perception, Learning, and Control", and at the NeurIPS2018 workshop on "Relational Representation Learning"

2005.08186 2020-07-24 cs.CV 57%

Co-occurrence Based Texture Synthesis

Anna Darzi, Itai Lang, Ashutosh Taklikar, Hadar Averbuch-Elor, Shai Avidan

专题命中可控生成：image generation(abstract)；分类 cs.CV

1912.09421 2020-07-20 cs.CV 57%

Neural Design Network: Graphic Layout Generation with Constraints

Hsin-Ying Lee, Lu Jiang, Irfan Essa, Phuong B Le, Haifeng Gong, Ming-Hsuan Yang, Weilong Yang

专题命中可控生成：image synthesis(abstract)；分类 cs.CV

Comments European Conference on Computer Vision (ECCV) 2020

2007.02190 2020-07-15 cs.CV cs.LG eess.IV 57%

BézierSketch: A generative model for scalable vector sketches

Ayan Das, Yongxin Yang, Timothy Hospedales, Tao Xiang, Yi-Zhe Song

专题命中可控生成：image generation(abstract)；分类 cs.CV

Comments Accepted as poster at ECCV 2020

2006.02051 2020-07-15 cs.CV 57%

Reference-guided Face Component Editing

Qiyao Deng, Jie Cao, Yunfan Liu, Zhenhua Chai, Qi Li, Zhenan Sun

专题命中可控生成：inpainting(abstract)；分类 cs.CV

2001.08572 2020-06-23 cs.LG cs.CV stat.ML 57%

Toward a Controllable Disentanglement Network

Zengjie Song, Oluwasanmi Koyejo, Jiangshe Zhang

专题命中可控生成：image editing(abstract)；分类 cs.CV

Comments Improved version of arXiv:1912.11675

2006.10649 2020-06-19 cs.CV 57%

Multi-Density Sketch-to-Image Translation Network

Jialu Huang, Jing Liao, Zhifeng Tan, Sam Kwong

专题命中可控生成：image synthesis(abstract)；分类 cs.CV

Comments 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

2006.05180 2020-06-11 cs.CV eess.IV 57%

Breaking the Limits of Remote Sensing by Simulation and Deep Learning for Flood and Debris Flow Mapping

Naoto Yokoya, Kazuki Yamanoi, Wei He, Gerald Baier, Bruno Adriano, Hiroyuki Miura, Satoru Oishi

专题命中可控生成：inpainting(abstract)；分类 cs.CV

2005.08045 2020-05-19 cs.CV 57%

Visual Relationship Detection using Scene Graphs: A Survey

Aniket Agarwal, Ayush Mangal, Vipul

专题命中可控生成：image generation(abstract)；分类 cs.CV

2005.05218 2020-05-12 eess.IV cs.CV 57%

Medical Image Segmentation Using a U-Net type of Architecture

Eshal Zahra, Bostan Ali, Wajahat Siddique

专题命中可控生成：image generation(abstract)；分类 cs.CV

Comments 6 Pages

2005.02066 2020-05-06 cs.CV 57%

Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation and Task Re-weighting

Dongnan Liu, Donghao Zhang, Yang Song, Fan Zhang, Lauren O'Donnell, Heng Huang, Mei Chen, Weidong Cai

专题命中可控生成：inpainting(abstract)；分类 cs.CV

Comments Accepted by CVPR2020

2004.09147 2020-04-21 cs.CV 57%

Cosmetic-Aware Makeup Cleanser

Yi Li, Huaibo Huang, Junchi Yu, Ran He, Tieniu Tan

专题命中可控生成：image generation(abstract)；分类 cs.CV

Comments Accepted by BTAS 2019 (the 10th IEEE International Conference on Biometrics: Theory, Applications and Systems)

1906.00709 2020-04-09 cs.CV cs.LG eess.IV 57%

cGANs with Conditional Convolution Layer

Min-Cheol Sagong, Yong-Goo Shin, Yoon-Jae Yeo, Seung Park, Sung-Jea Ko

专题命中可控生成：image generation(abstract)；分类 cs.CV

Comments Submitted to IEEE Trans. Neural Networks and Learning Systems (TNNLS)

2004.01166 2020-04-03 cs.CV 57%

Bodies at Rest: 3D Human Pose and Shape Estimation from a Pressure Image using Synthetic Data

Henry M. Clever, Zackory Erickson, Ariel Kapusta, Greg Turk, C. Karen Liu, Charles C. Kemp

专题命中可控生成：image generation(abstract)；分类 cs.CV

Comments 18 pages, 18 figures, 5 tables. Accepted for oral presentation at CVPR 2020

1. 可控生成 4216 篇

JGAN: A Joint Formulation of GAN for Synthesizing Images and Labels

Empty Cities: a Dynamic-Object-Invariant Space for Visual SLAM

JUMPS: Joints Upsampling Method for Pose Sequences

Intuitive Facial Animation Editing Based On A Generative RNN Framework

MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination

Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumes

Synthetic Convolutional Features for Improved Semantic Segmentation

Fighting Deepfake by Exposing the Convolutional Traces on Images

View-consistent 4D Light Field Depth Estimation

Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation

Semantic View Synthesis

MTRNet++: One-stage Mask-based Scene Text Eraser

MMM : Exploring Conditional Multi-Track Music Generation with the Transformer

Category Level Object Pose Estimation via Neural Analysis-by-Synthesis

Implanting Synthetic Lesions for Improving Liver Lesion Segmentation in CT Exams

TSIT: A Simple and Versatile Framework for Image-to-Image Translation

Investigating Object Compositionality in Generative Adversarial Networks

Co-occurrence Based Texture Synthesis

Neural Design Network: Graphic Layout Generation with Constraints

BézierSketch: A generative model for scalable vector sketches

Reference-guided Face Component Editing

Toward a Controllable Disentanglement Network

Multi-Density Sketch-to-Image Translation Network

Breaking the Limits of Remote Sensing by Simulation and Deep Learning for Flood and Debris Flow Mapping

Visual Relationship Detection using Scene Graphs: A Survey

Medical Image Segmentation Using a U-Net type of Architecture

Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation and Task Re-weighting

Cosmetic-Aware Makeup Cleanser

cGANs with Conditional Convolution Layer

Bodies at Rest: 3D Human Pose and Shape Estimation from a Pressure Image using Synthetic Data