图像生成 - arXivDaily 专题

2212.11984 2022-12-23 cs.CV 57%

DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesis

Yinghao Xu, Menglei Chai, Zifan Shi, Sida Peng, Ivan Skorokhodov, Aliaksandr Siarohin, Ceyuan Yang, Yujun Shen, Hsin-Ying Lee, Bolei Zhou, Sergey Tulyakov

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

Comments Project page: https://snap-research.github.io/discoscene/

2205.01536 2022-12-09 cs.CV cs.LG 57%

BiOcularGAN: Bimodal Synthesis and Annotation of Ocular Images

Darian Tomašević, Peter Peer, Vitomir Štruc

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

Comments 13 pages, 14 figures

2212.03237 2022-12-07 cs.CV 57%

RANA: Relightable Articulated Neural Avatars

Umar Iqbal, Akin Caliskan, Koki Nagano, Sameh Khamis, Pavlo Molchanov, Jan Kautz

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

Comments project page: https://nvlabs.github.io/RANA/

2211.16696 2022-12-02 eess.IV cs.CV cs.LG 57%

Automated anomaly-aware 3D segmentation of bones and cartilages in knee MR images from the Osteoarthritis Initiative

Boyeong Woo, Craig Engstrom, William Baresic, Jurgen Fripp, Stuart Crozier, Shekhar S. Chandra

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

2211.16798 2022-12-01 cs.CV cs.LG 57%

Dr.3D: Adapting 3D GANs to Artistic Drawings

Wonjoon Jin, Nuri Ryu, Geonung Kim, Seung-Hwan Baek, Sunghyun Cho

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

Comments Accepted to SIGGRAPH Asia 2022 (Conference Track). For project page, see https://jinwonjoon.github.io/dr3d/

2211.16710 2022-12-01 cs.CV cs.AI cs.LG 57%

Extracting Semantic Knowledge from GANs with Unsupervised Learning

Jianjin Xu, Zhaoxiang Zhang, Xiaolin Hu

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

2211.12209 2022-11-23 cs.CV 57%

$S^2$-Flow: Joint Semantic and Style Editing of Facial Images

Krishnakant Singh, Simone Schaub-Meyer, Stefan Roth

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

Comments Accepted to BMVC 2022

2211.10715 2022-11-22 cs.CV 57%

Single Stage Multi-Pose Virtual Try-On

Sen He, Yi-Zhe Song, Tao Xiang

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

2211.06119 2022-11-18 cs.CV 57%

SSGVS: Semantic Scene Graph-to-Video Synthesis

Yuren Cong, Jinhui Yi, Bodo Rosenhahn, Michael Ying Yang

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

2211.07195 2022-11-15 cs.CV 57%

Controllable GAN Synthesis Using Non-Rigid Structure-from-Motion

René Haas, Stella Graßhof, Sami S. Brandt

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

2211.02707 2022-11-08 cs.CV 57%

Contrastive Learning for Diverse Disentangled Foreground Generation

Yuheng Li, Yijun Li, Jingwan Lu, Eli Shechtman, Yong Jae Lee, Krishna Kumar Singh

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

Comments ECCV 2022

2210.12682 2022-10-25 cs.CV cs.RO 57%

Photo-realistic Neural Domain Randomization

Sergey Zakharov, Rares Ambrus, Vitor Guizilini, Wadim Kehl, Adrien Gaidon

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

Comments Accepted to European Conference on Computer Vision (ECCV), 2022

2210.07301 2022-10-18 cs.CV 57%

3D GAN Inversion with Pose Optimization

Jaehoon Ko, Kyusun Cho, Daewon Choi, Kwangrok Ryoo, Seungryong Kim

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

Comments Project Page: https://3dgan-inversion.github.io

2210.05891 2022-10-13 cs.CV 57%

Point Cloud Scene Completion with Joint Color and Semantic Estimation from Single RGB-D Image

Zhaoxuan Zhang, Xiaoguang Han, Bo Dong, Tong Li, Baocai Yin, Xin Yang

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

Comments arXiv admin note: substantial text overlap with arXiv:1903.04019

2210.05825 2022-10-13 cs.CV cs.AI 57%

Controllable Radiance Fields for Dynamic Face Synthesis

Peiye Zhuang, Liqian Ma, Oluwasanmi Koyejo, Alexander G. Schwing

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

Comments Accepted to 3DV 2022. 13 pages, 15 figures

2210.04883 2022-10-11 cs.CV cs.AI cs.LG 57%

SCAM! Transferring humans between images with Semantic Cross Attention Modulation

Nicolas Dufour, David Picard, Vicky Kalogeiton

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

Comments Accepted at ECCV 2022

2210.04553 2022-10-11 cs.CV 57%

SiNeRF: Sinusoidal Neural Radiance Fields for Joint Pose Estimation and Scene Reconstruction

Yitong Xia, Hao Tang, Radu Timofte, Luc Van Gool

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

Comments Accepted yet not published by BMVC2022

2210.02206 2022-10-06 cs.MM 57%

Improving Visual-Semantic Embedding with Adaptive Pooling and Optimization Objective

Zijian Zhang, Chang Shu, Ya Xiao, Yuan Shen, Di Zhu, Jing Xiao, Youxin Chen, Jey Han Lau, Qian Zhang, Zheng Lu

专题命中可控生成：text-to-image(abstract)；分类 cs.MM

2206.08916 2022-10-06 cs.CV 57%

Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks

Jiasen Lu, Christopher Clark, Rowan Zellers, Roozbeh Mottaghi, Aniruddha Kembhavi

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

2210.01436 2022-10-05 cs.CV 57%

Non-learning Stereo-aided Depth Completion under Mis-projection via Selective Stereo Matching

Yasuhiro Yao, Ryoichi Ishikawa, Shingo Ando, Kana Kurata, Naoki Ito, Jun Shimamura, Takeshi Oishi

专题命中可控生成：diffusion(abstract)；分类 cs.CV

Comments 15 pages, 13 figures

Journal ref in IEEE Access, vol. 9, pp. 136674-136686, 2021

2209.03160 2022-09-09 cs.CV 57%

AI Illustrator: Translating Raw Descriptions into Images by Prompt-based Cross-Modal Generation

Yiyang Ma, Huan Yang, Bei Liu, Jianlong Fu, Jiaying Liu

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

2107.06149 2022-08-31 cs.CV 57%

MINERVAS: Massive INterior EnviRonments VirtuAl Synthesis

Haocheng Ren, Hao Zhang, Jia Zheng, Jiaxiang Zheng, Rui Tang, Yuchi Huo, Hujun Bao, Rui Wang

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

Comments Accepted by Computer Graphics Forum, Pacific Graphics 2022. The two first authors contribute equally. Project pape: https://coohom.github.io/MINERVAS

2208.12934 2022-08-30 cs.CV 57%

xCloth: Extracting Template-free Textured 3D Clothes from a Monocular Image

Astitva Srivastava, Chandradeep Pokhariya, Sai Sagar Jinka, Avinash Sharma

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

Comments Accepted at ACM Multimedia-2022

2104.06773 2022-08-19 cs.CV 57%

HoughNet: Integrating near and long-range evidence for visual detection

Nermin Samet, Samet Hicsonmez, Emre Akbas

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

Comments accepted to the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). arXiv admin note: substantial text overlap with arXiv:2007.02355

2208.07862 2022-08-17 cs.CV 57%

StyleFaceV: Face Video Generation via Decomposing and Recomposing Pretrained StyleGAN3

Haonan Qiu, Yuming Jiang, Hang Zhou, Wayne Wu, Ziwei Liu

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

Comments Project Page: http://haonanqiu.com/projects/StyleFaceV.html; Code Repo: https://github.com/arthur-qiu/StyleFaceV

2208.07496 2022-08-17 cs.CV 57%

SGM-Net: Semantic Guided Matting Net

Qing Song, Wenfeng Sun, Donghan Yang, Mengjie Hu, Chun Liu

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

2010.00029 2022-08-16 cs.LG cond-mat.dis-nn cs.AI cs.CV stat.ML 57%

RG-Flow: A hierarchical and explainable flow model based on renormalization group and sparse prior

Hong-Ye Hu, Dian Wu, Yi-Zhuang You, Bruno Olshausen, Yubei Chen

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

Comments 31 pages, 20 figures, 3 tables

Journal ref Mach. Learn.: Sci. Technol. 3 035009 (2022)

2208.05621 2022-08-12 cs.CV 57%

ARMANI: Part-level Garment-Text Alignment for Unified Cross-Modal Fashion Design

Xujie Zhang, Yu Sha, Michael C. Kampffmeyer, Zhenyu Xie, Zequn Jie, Chengwen Huang, Jianqing Peng, Xiaodan Liang

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

Comments Accepted by ACMMM22

2208.04517 2022-08-10 cs.CV 57%

Attribute Controllable Beautiful Caucasian Face Generation by Aesthetics Driven Reinforcement Learning

Xin Jin, Shu Zhao, Le Zhang, Xin Zhao, Qiang Deng, Chaoen Xiao

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

Comments 13 pages, 5 figures. ACM Multimedia 2022 Technical Demos and Videos Program

2208.03327 2022-08-09 eess.IV cs.CV 57%

Seamless Iterative Semi-Supervised Correction of Imperfect Labels in Microscopy Images

Marawan Elbatel, Christina Bornberg, Manasi Kattel, Enrique Almar, Claudio Marrocco, Alessandro Bria

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

Comments To appear at MICCAI 2022 Workshop on Domain Adaptation and Representation Transfer (DART)

1. 可控生成 4216 篇

DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesis

BiOcularGAN: Bimodal Synthesis and Annotation of Ocular Images

RANA: Relightable Articulated Neural Avatars

Automated anomaly-aware 3D segmentation of bones and cartilages in knee MR images from the Osteoarthritis Initiative

Dr.3D: Adapting 3D GANs to Artistic Drawings

Extracting Semantic Knowledge from GANs with Unsupervised Learning

$S^2$-Flow: Joint Semantic and Style Editing of Facial Images

Single Stage Multi-Pose Virtual Try-On

SSGVS: Semantic Scene Graph-to-Video Synthesis

Controllable GAN Synthesis Using Non-Rigid Structure-from-Motion

Contrastive Learning for Diverse Disentangled Foreground Generation

Photo-realistic Neural Domain Randomization

3D GAN Inversion with Pose Optimization

Point Cloud Scene Completion with Joint Color and Semantic Estimation from Single RGB-D Image

Controllable Radiance Fields for Dynamic Face Synthesis

SCAM! Transferring humans between images with Semantic Cross Attention Modulation

SiNeRF: Sinusoidal Neural Radiance Fields for Joint Pose Estimation and Scene Reconstruction

Improving Visual-Semantic Embedding with Adaptive Pooling and Optimization Objective

Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks

Non-learning Stereo-aided Depth Completion under Mis-projection via Selective Stereo Matching

AI Illustrator: Translating Raw Descriptions into Images by Prompt-based Cross-Modal Generation

MINERVAS: Massive INterior EnviRonments VirtuAl Synthesis

xCloth: Extracting Template-free Textured 3D Clothes from a Monocular Image

HoughNet: Integrating near and long-range evidence for visual detection

StyleFaceV: Face Video Generation via Decomposing and Recomposing Pretrained StyleGAN3

SGM-Net: Semantic Guided Matting Net

RG-Flow: A hierarchical and explainable flow model based on renormalization group and sparse prior

ARMANI: Part-level Garment-Text Alignment for Unified Cross-Modal Fashion Design

Attribute Controllable Beautiful Caucasian Face Generation by Aesthetics Driven Reinforcement Learning

Seamless Iterative Semi-Supervised Correction of Imperfect Labels in Microscopy Images