图像生成 - arXivDaily 专题

2404.10685 2024-04-17 cs.CV cs.GR 62%

Generating Human Interaction Motions in Scenes with Text Control

Hongwei Yi, Justus Thies, Michael J. Black, Xue Bin Peng, Davis Rempe

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

Comments Project Page: https://research.nvidia.com/labs/toronto-ai/tesmo/

2310.08580 2024-04-16 cs.CV cs.GR 62%

OmniControl: Control Any Joint at Any Time for Human Motion Generation

Yiming Xie, Varun Jampani, Lei Zhong, Deqing Sun, Huaizu Jiang

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

Comments ICLR 2024. Project page: https://neu-vi.github.io/omnicontrol/

2404.00676 2024-04-02 cs.CV cs.GR 62%

OmniLocalRF: Omnidirectional Local Radiance Fields from Dynamic Videos

Dongyoung Choi, Hyeonjoong Jang, Min H. Kim

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

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024

2401.01647 2024-03-28 cs.CV cs.GR 62%

SIGNeRF: Scene Integrated Generation for Neural Radiance Fields

Jan-Niklas Dihlmann, Andreas Engelhardt, Hendrik Lensch

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

Comments Project Page: https://signerf.jdihlmann.com

2402.02369 2024-02-06 cs.CV cs.CL cs.MM 62%

M$^3$Face: A Unified Multi-Modal Multilingual Framework for Human Face Generation and Editing

Mohammadreza Mofayezi, Reza Alipour, Mohammad Ali Kakavand, Ehsaneddin Asgari

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

2401.03764 2024-01-09 cs.CV cs.GR 62%

3D-SSGAN: Lifting 2D Semantics for 3D-Aware Compositional Portrait Synthesis

Ruiqi Liu, Peng Zheng, Ye Wang, Rui Ma

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

2301.13591 2023-11-15 cs.CV cs.MM 62%

Zero3D: Semantic-Driven Multi-Category 3D Shape Generation

Bo Han, Yitong Fu, Yixuan Shen

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

Comments work in progress

2310.15247 2023-10-25 cs.SD cs.CV cs.LG cs.MM eess.AS 62%

SyncFusion: Multimodal Onset-synchronized Video-to-Audio Foley Synthesis

Marco Comunità, Riccardo F. Gramaccioni, Emilian Postolache, Emanuele Rodolà, Danilo Comminiello, Joshua D. Reiss

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

2310.12678 2023-10-20 cs.GR cs.CV 62%

TapMo: Shape-aware Motion Generation of Skeleton-free Characters

Jiaxu Zhang, Shaoli Huang, Zhigang Tu, Xin Chen, Xiaohang Zhan, Gang Yu, Ying Shan

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

2308.09678 2023-10-17 cs.CV cs.AI cs.MM cs.RO 62%

PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimation

Hanbing Liu, Jun-Yan He, Zhi-Qi Cheng, Wangmeng Xiang, Qize Yang, Wenhao Chai, Gaoang Wang, Xu Bao, Bin Luo, Yifeng Geng, Xuansong Xie

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

Comments Accepted to ACM Multimedia 2023; 10 pages, 4 figures, 8 tables; the code is at https://github.com/hbing-l/PoSynDA

2310.06138 2023-10-11 cs.CV cs.AI cs.LG cs.MM cs.RO 62%

Layout Sequence Prediction From Noisy Mobile Modality

Haichao Zhang, Yi Xu, Hongsheng Lu, Takayuki Shimizu, Yun Fu

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

Comments In Proceedings of the 31st ACM International Conference on Multimedia 2023 (MM 23)

2212.04636 2023-08-29 cs.CV cs.GR 62%

Ego-Body Pose Estimation via Ego-Head Pose Estimation

Jiaman Li, C. Karen Liu, Jiajun Wu

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

Comments CVPR 2023 (Award Candidate)

2306.07476 2023-06-14 cs.CV cs.GR 62%

AniFaceDrawing: Anime Portrait Exploration during Your Sketching

Zhengyu Huang, Haoran Xie, Tsukasa Fukusato, Kazunori Miyata

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

Comments 11 pages, 13 figures. SIGGRAPH 2023 Conference Track. Project webpage: http://www.jaist.ac.jp/~xie/AniFaceDrawing.html

2305.02618 2023-05-05 cs.CV cs.GR 62%

Semantic-aware Generation of Multi-view Portrait Drawings

Biao Ma, Fei Gao, Chang Jiang, Nannan Wang, Gang Xu

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

Comments Accepted by IJCAI 2023

2304.00838 2023-04-04 cs.CV cs.GR 62%

MetaHead: An Engine to Create Realistic Digital Head

Dingyun Zhang, Chenglai Zhong, Yudong Guo, Yang Hong, Juyong Zhang

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

Comments Project page: https://ustc3dv.github.io/MetaHead/

2303.13450 2023-03-24 cs.CV cs.GR cs.LG 62%

Set-the-Scene: Global-Local Training for Generating Controllable NeRF Scenes

Dana Cohen-Bar, Elad Richardson, Gal Metzer, Raja Giryes, Daniel Cohen-Or

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

Comments project page at https://danacohen95.github.io/Set-the-Scene/

2303.01818 2023-03-07 cs.CV cs.AI cs.GR 62%

Word-As-Image for Semantic Typography

Shir Iluz, Yael Vinker, Amir Hertz, Daniel Berio, Daniel Cohen-Or, Ariel Shamir

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

2212.04970 2022-12-12 cs.CV cs.AI cs.GR 62%

Masked Lip-Sync Prediction by Audio-Visual Contextual Exploitation in Transformers

Yasheng Sun, Hang Zhou, Kaisiyuan Wang, Qianyi Wu, Zhibin Hong, Jingtuo Liu, Errui Ding, Jingdong Wang, Ziwei Liu, Hideki Koike

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

Comments Accepted to SIGGRAPH Asia 2022 (Conference Proceedings). Project page: https://hangz-nju-cuhk.github.io/projects/AV-CAT

2210.17344 2022-11-01 cs.GR cs.CV 62%

gCoRF: Generative Compositional Radiance Fields

Mallikarjun BR, Ayush Tewari, Xingang Pan, Mohamed Elgharib, Christian Theobalt

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

Comments https://vcai.mpi-inf.mpg.de/projects/gCoRF/

2209.06970 2022-10-18 cs.CV cs.GR cs.LG 62%

Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Models

Chen Henry Wu, Saman Motamed, Shaunak Srivastava, Fernando De la Torre

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

Comments NeurIPS 2022

2112.03258 2022-09-16 cs.CV cs.GR 62%

DoodleFormer: Creative Sketch Drawing with Transformers

Ankan Kumar Bhunia, Salman Khan, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Shahbaz Khan, Jorma Laaksonen, Michael Felsberg

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

Comments Accepted to ECCV-2022. Project webpage: https://ankanbhunia.github.io/doodleformer/

2207.00256 2022-08-31 cs.CV cs.GR 62%

Unsupervised High-Resolution Portrait Gaze Correction and Animation

Jichao Zhang, Jingjing Chen, Hao Tang, Enver Sangineto, Peng Wu, Yan Yan, Nicu Sebe, Wei Wang

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

Comments Accepted to TIP. arXiv admin note: text overlap with arXiv:2008.03834

2112.13889 2022-08-03 cs.CV cs.GR 62%

Free-Viewpoint RGB-D Human Performance Capture and Rendering

Phong Nguyen-Ha, Nikolaos Sarafianos, Christoph Lassner, Janne Heikkila, Tony Tung

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

Comments Accepted at ECCV 2022, Project page: https://www.phongnhhn.info/HVS_Net/index.html

2205.13996 2022-06-01 cs.CV cs.GR 62%

Video2StyleGAN: Disentangling Local and Global Variations in a Video

Rameen Abdal, Peihao Zhu, Niloy J. Mitra, Peter Wonka

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

Comments Video : https://youtu.be/oUeXFyfdE1A

2205.11733 2022-05-25 cs.CV cs.GR 62%

Single-View View Synthesis in the Wild with Learned Adaptive Multiplane Images

Yuxuan Han, Ruicheng Wang, Jiaolong Yang

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

Comments ACM SIGGRAPH 2022. Project page: https://yxuhan.github.io/AdaMPI/

2204.10477 2022-05-05 cs.CV cs.GR 62%

Learning Dynamic View Synthesis With Few RGBD Cameras

Shengze Wang, YoungJoong Kwon, Yuan Shen, Qian Zhang, Andrei State, Jia-Bin Huang, Henry Fuchs

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

Comments One of the coauthors believes that this work should be improved more before releasing it on arXiv, and thus suggested withdrawing this paper. There will not be a replacement for this paper

2201.09689 2022-01-25 cs.CV cs.AI cs.LG cs.MM 62%

Which Style Makes Me Attractive? Interpretable Control Discovery and Counterfactual Explanation on StyleGAN

Bo Li, Qiulin Wang, Jiquan Pei, Yu Yang, Xiangyang Ji

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

2111.01048 2021-11-02 cs.CV cs.AI cs.GR cs.LG 62%

MOST-GAN: 3D Morphable StyleGAN for Disentangled Face Image Manipulation

Safa C. Medin, Bernhard Egger, Anoop Cherian, Ye Wang, Joshua B. Tenenbaum, Xiaoming Liu, Tim K. Marks

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

2110.08872 2021-10-19 cs.CV cs.IR cs.LG cs.MM 62%

Contrastive Learning of Visual-Semantic Embeddings

Anurag Jain, Yashaswi Verma

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

2109.09378 2021-09-21 cs.GR cs.CV 62%

FreeStyleGAN: Free-view Editable Portrait Rendering with the Camera Manifold

Thomas Leimkühler, George Drettakis

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

Comments Project webpage: https://repo-sam.inria.fr/fungraph/freestylegan/

Journal ref ACM Transactions on Graphics (SIGGRAPH Asia 2021)

1. 可控生成 4228 篇

Generating Human Interaction Motions in Scenes with Text Control

OmniControl: Control Any Joint at Any Time for Human Motion Generation

OmniLocalRF: Omnidirectional Local Radiance Fields from Dynamic Videos

SIGNeRF: Scene Integrated Generation for Neural Radiance Fields

M$^3$Face: A Unified Multi-Modal Multilingual Framework for Human Face Generation and Editing

3D-SSGAN: Lifting 2D Semantics for 3D-Aware Compositional Portrait Synthesis

Zero3D: Semantic-Driven Multi-Category 3D Shape Generation

SyncFusion: Multimodal Onset-synchronized Video-to-Audio Foley Synthesis

TapMo: Shape-aware Motion Generation of Skeleton-free Characters

PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose Estimation

Layout Sequence Prediction From Noisy Mobile Modality

Ego-Body Pose Estimation via Ego-Head Pose Estimation

AniFaceDrawing: Anime Portrait Exploration during Your Sketching

Semantic-aware Generation of Multi-view Portrait Drawings

MetaHead: An Engine to Create Realistic Digital Head

Set-the-Scene: Global-Local Training for Generating Controllable NeRF Scenes

Word-As-Image for Semantic Typography

Masked Lip-Sync Prediction by Audio-Visual Contextual Exploitation in Transformers

gCoRF: Generative Compositional Radiance Fields

Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Models

DoodleFormer: Creative Sketch Drawing with Transformers

Unsupervised High-Resolution Portrait Gaze Correction and Animation

Free-Viewpoint RGB-D Human Performance Capture and Rendering

Video2StyleGAN: Disentangling Local and Global Variations in a Video

Single-View View Synthesis in the Wild with Learned Adaptive Multiplane Images

Learning Dynamic View Synthesis With Few RGBD Cameras

Which Style Makes Me Attractive? Interpretable Control Discovery and Counterfactual Explanation on StyleGAN

MOST-GAN: 3D Morphable StyleGAN for Disentangled Face Image Manipulation

Contrastive Learning of Visual-Semantic Embeddings

FreeStyleGAN: Free-view Editable Portrait Rendering with the Camera Manifold