Filters








1,813 Hits in 4.4 sec

Efficient Geometry-aware 3D Generative Adversarial Networks [article]

Eric R. Chan, Connor Z. Lin, Matthew A. Chan, Koki Nagano, Boxiao Pan, Shalini De Mello, Orazio Gallo, Leonidas Guibas, Jonathan Tremblay, Sameh Khamis, Tero Karras, Gordon Wetzstein
2022 arXiv   pre-print
produces high-quality 3D geometry.  ...  We demonstrate state-of-the-art 3D-aware synthesis with FFHQ and AFHQ Cats, among other experiments.  ...  Generative 3D-aware image synthesis. Generative adversarial networks [16] have recently achieved photorealistic image quality for 2D image synthesis [25, 28, 29, 55] .  ... 
arXiv:2112.07945v2 fatcat:diysjwesgfbl7hlf2yn3s3lhb4

VoLux-GAN: A Generative Model for 3D Face Synthesis with HDRI Relighting [article]

Feitong Tan, Sean Fanello, Abhimitra Meka, Sergio Orts-Escolano, Danhang Tang, Rohit Pandey, Jonathan Taylor, Ping Tan, Yinda Zhang
2022 arXiv   pre-print
We propose VoLux-GAN, a generative framework to synthesize 3D-aware faces with convincing relighting.  ...  Multiple experiments and comparisons with other generative frameworks show how our model is a step forward towards photorealistic relightable 3D generative models.  ...  In this work, we propose a 3D aware generative model with HDRI relighting supervised by adversarial losses.  ... 
arXiv:2201.04873v1 fatcat:hkxwjzghvzanhgtw7vardumrqe

ShapeAdv: Generating Shape-Aware Adversarial 3D Point Clouds [article]

Kibok Lee, Zhuoyuan Chen, Xinchen Yan, Raquel Urtasun, Ersin Yumer
2020 arXiv   pre-print
Our shape-aware adversarial attacks are orthogonal to existing point cloud based attacks and shed light on the vulnerability of 3D deep neural networks.  ...  We develop shape-aware adversarial 3D point cloud attacks by leveraging the learned latent space of a point cloud auto-encoder where the adversarial noise is applied in the latent space.  ...  To summarize, the contributions of our shape-aware adversarial 3D point cloud generation are as follows: -We introduce a novel framework for generating shape-aware adversarial 3D point clouds by injecting  ... 
arXiv:2005.11626v1 fatcat:derfn55asneibdpoyblzaoeldy

Geometry-Aware Generation of Adversarial Point Clouds [article]

Yuxin Wen, Jiehong Lin, Ke Chen, C. L. Philip Chen, Kui Jia
2020 arXiv   pre-print
Regularizing the targeted attack loss with our proposed geometry-aware objectives results in our proposed method, Geometry-Aware Adversarial Attack (GeoA^3).  ...  Motivated by the different mechanisms by which humans perceive 2D images and 3D shapes, in this paper we propose the new design of geometry-aware objectives, whose solutions favor (the discrete versions  ...  Deep Learning Point Cloud/Surface Reconstruction -Our proposed geometry-aware generation of adversarial point clouds is also related to recent methods that learn deep networks to generate 3D surface shapes  ... 
arXiv:1912.11171v3 fatcat:moalrm26nnd2vnedlcwqvkvema

Transformation-Grounded Image Generation Network for Novel 3D View Synthesis

Eunbyung Park, Jimei Yang, Ersin Yumer, Duygu Ceylan, Alexander C. Berg
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
We present a transformation-grounded image generation network for novel 3D view synthesis from a single image.  ...  In addition to the new network structure, training with a combination of adversarial and perceptual loss results in a reduction in common artifacts of novel view synthesis such as distortions and holes  ...  Also, multiple generated 2D views form an efficient representation for 3D reconstruction [37] .  ... 
doi:10.1109/cvpr.2017.82 dblp:conf/cvpr/ParkYYCB17 fatcat:ltj2uqgrvje65lpo7h2fozbdze

Transformation-Grounded Image Generation Network for Novel 3D View Synthesis [article]

Eunbyung Park, Jimei Yang, Ersin Yumer, Duygu Ceylan, Alexander C. Berg
2017 arXiv   pre-print
We present a transformation-grounded image generation network for novel 3D view synthesis from a single image.  ...  In addition to the new network structure, training with a combination of adversarial and perceptual loss results in a reduction in common artifacts of novel view synthesis such as distortions and holes  ...  Also, multiple generated 2D views form an efficient representation for 3D reconstruction [36] .  ... 
arXiv:1703.02921v1 fatcat:acvd3262zrg7ra7rwajo3tg65q

IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration [article]

Ziyi Wu, Yueqi Duan, He Wang, Qingnan Fan, Leonidas J. Guibas
2021 arXiv   pre-print
More specifically, we propose an IF-Defense framework to directly optimize the coordinates of input points with geometry-aware and distribution-aware constraints.  ...  However, those deep neural networks are vulnerable to various 3D adversarial attacks, which can be summarized as two primary types: point perturbation that affects local point distribution, and surface  ...  LG-GAN [37] is a generation based 3D attack method, which leverages GANs [9] to generate adversarial point clouds guided by the input target labels.  ... 
arXiv:2010.05272v3 fatcat:akirmqng2bcidnapddb5p7b6aa

FENeRF: Face Editing in Neural Radiance Fields [article]

Jingxiang Sun, Xuan Wang, Yong Zhang, Xiaoyu Li, Qi Zhang, Yebin Liu, Jue Wang
2022 arXiv   pre-print
Previous portrait image generation methods roughly fall into two categories: 2D GANs and 3D-aware GANs. 2D GANs can generate high fidelity portraits but with low view consistency. 3D-aware GAN methods  ...  Our method uses two decoupled latent codes to generate corresponding facial semantics and texture in a spatial aligned 3D volume with shared geometry.  ...  On the other, our joint rendering enhances the quality of semantic, geometry and texture at the same time. 3D-aware generative network.  ... 
arXiv:2111.15490v2 fatcat:qtqaijbwhncn7g3ncwjraehr6q

VCIP 2020 Index

2020 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)  
of Point Clou and Multiple Views for 3D Shape Recognition Lei, Xuejing Noise-Aware Texture-Preserving Low-Light Enhancement Lei, Zhengchao Efficient Light Deep Network for Street Scene Parsing  ...  On 2D-3D Image Feature Detections for Image To-Geometry Registration in Virtual Dental Mod Prawiro, Herman An Empirical Study of Emotion Recognition fro Thermal Video Based on Deep Neural Network  ... 
doi:10.1109/vcip49819.2020.9301896 fatcat:bdh7cuvstzgrbaztnahjdp5s5y

A Tetrahedron-Based Heat Flux Signature for Cortical Thickness Morphometry Analysis [chapter]

Yonghui Fan, Gang Wang, Natasha Lepore, Yalin Wang
2018 Lecture Notes in Computer Science  
Coupled Hidden Markov Models 668 Efficient Groupwise Registration for MR Brain Images via Hierarchical Graph Set Shrinkage 669 Conditional Generative Adversarial Networks for Metal Artifact Reduction  ...  442 Generative Invertible Networks (GIN): Pathophysiology-Interpretable Feature Mapping and Virtual Patient Generation 449 A multi-scale pyramid of 3D fully convolutional networks for abdominal multi-organ  ... 
doi:10.1007/978-3-030-00931-1_48 pmid:30338317 pmcid:PMC6191198 fatcat:dqhvpm5xzrdqhglrfftig3qejq

APB2FaceV2: Real-Time Audio-Guided Multi-Face Reenactment [article]

Jiangning Zhang, Xianfang Zeng, Chao Xu, Jun Chen, Yong Liu, Yunliang Jiang
2020 arXiv   pre-print
However, current methods can only reenact a special person once the model is trained or need extra operations such as 3D rendering and image post-fusion on the premise of generating vivid faces.  ...  network as our backbone so that the network can run in real time on CPU and GPU.  ...  RELATED WORKS Generative Adversarial Networks.  ... 
arXiv:2010.13017v1 fatcat:cgglya3urrh7nmbpjqmai37afa

A Registration-aided Domain Adaptation Network for 3D Point Cloud Based Place Recognition [article]

Zhijian Qiao, Hanjiang Hu, Weiang Shi, Siyuan Chen, Zhe Liu, Hesheng Wang
2021 arXiv   pre-print
To this end, a novel registration-aided 3D domain adaptation network for point cloud based place recognition is proposed.  ...  A structure-aware registration network is introduced to help to learn features with geometric information and a 6-DoFs pose between two point clouds with partial overlap can be estimated.  ...  A structure-aware registration network is proposed to leverage geometry property and co-contextual information between two input point clouds.  ... 
arXiv:2012.05018v2 fatcat:qojrmgenfbavlfd6ogwfaawkxe

2021 Index IEEE Transactions on Multimedia Vol. 23

2021 IEEE transactions on multimedia  
., +, TMM 2021 3059-3072 DLGAN: Depth-Preserving Latent Generative Adversarial Network for 3D Reconstruction.  ...  Fan, B., +, TMM 2021 2770-2781 DLGAN: Depth-Preserving Latent Generative Adversarial Network for 3D Reconstruction.  ...  ., Low-Rank Pairwise Align- ment Bilinear Network For Few-Shot Fine-Grained Image Classification; TMM 2021 1666-1680 Huang, H., see 1855 -1867 Huang, H., see Jiang, X., TMM 2021 2602-2613 Huang, J.,  ... 
doi:10.1109/tmm.2022.3141947 fatcat:lil2nf3vd5ehbfgtslulu7y3lq

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
., +, TIP 2021 6212-6225 Incremental Generative Occlusion Adversarial Suppression Network for Person ReID. Zhao, C., +, TIP 2021 4212-4224 Is Context-Aware CNN Ready for the Surroundings?  ...  Direct Unsupervised Super-Resolution Using Generative Adversarial Network (DUS-GAN) for Real-World Data.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu

2020 Index IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 42

2021 IEEE Transactions on Pattern Analysis and Machine Intelligence  
., +, TPAMI May 2020 1025-1037 Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization.  ...  Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization. Chen, Y., +, TPAMI July 2020 1654-1669 Asymmetric Mapping Quantization for Nearest Neighbor Search.  ...  Object recognition Adversarial Action Prediction Networks. Kong, Y., +, TPAMI March 2020 539-553 Capturing the Geometry of Object Categories from Video Supervision.  ... 
doi:10.1109/tpami.2020.3036557 fatcat:3j6s2l53x5eqxnlsptsgbjeebe
« Previous Showing results 1 — 15 out of 1,813 results