多模态大模型 - arXivDaily 专题

2312.01904 2023-12-05 cs.CV cs.LG eess.IV 57%

Unsupervised Anomaly Detection using Aggregated Normative Diffusion

Alexander Frotscher, Jaivardhan Kapoor, Thomas Wolfers, Christian F. Baumgartner

专题命中多模态生成：multi-modal(abstract)；分类 cs.CV

2306.00783 2023-12-05 cs.CV 57%

FaceDNeRF: Semantics-Driven Face Reconstruction, Prompt Editing and Relighting with Diffusion Models

Hao Zhang, Yanbo Xu, Tianyuan Dai, Yu-Wing Tai, Chi-Keung Tang

专题命中多模态生成：multi-modal(abstract)；分类 cs.CV

2311.17917 2023-11-30 cs.GR cs.CV 57%

AvatarStudio: High-fidelity and Animatable 3D Avatar Creation from Text

Jianfeng Zhang, Xuanmeng Zhang, Huichao Zhang, Jun Hao Liew, Chenxu Zhang, Yi Yang, Jiashi Feng

专题命中多模态生成：multimodal(abstract)；分类 cs.CV

Comments Project page at http://jeff95.me/projects/avatarstudio.html

2212.10240 2023-11-30 cs.CL 57%

Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning

Lihua Qian, Mingxuan Wang, Yang Liu, Hao Zhou

专题命中多模态生成：multi-modal(abstract)；分类 cs.CL

Comments 8 pages, 7 figures

2310.20604 2023-11-29 eess.IV cs.CV 57%

Enhanced Synthetic MRI Generation from CT Scans Using CycleGAN with Feature Extraction

Saba Nikbakhsh, Lachin Naghashyar, Morteza Valizadeh, Mehdi Chehel Amirani

专题命中多模态生成：multimodal(abstract)；分类 cs.CV

Comments 6 pages, 5 figures

2311.14301 2023-11-27 cs.CV cs.LG 57%

GeoViT: A Versatile Vision Transformer Architecture for Geospatial Image Analysis

Madhav Khirwar, Ankur Narang

专题命中多模态生成：multimodal(abstract)；分类 cs.CV

Comments Extended Abstract, Preprint

2305.11818 2023-11-22 cs.CV 57%

MaGIC: Multi-modality Guided Image Completion

Yongsheng Yu, Hao Wang, Tiejian Luo, Heng Fan, Libo Zhang

专题命中多模态生成：multi-modal(abstract)；分类 cs.CV

Comments 23 pages, 15 figures

2311.11238 2023-11-21 cs.HC cs.AI 57%

AtomXR: Streamlined XR Prototyping with Natural Language and Immersive Physical Interaction

Alice Cai, Caine Ardayfio, AnhPhu Nguyen, Tica Lin, Elena Glassman

专题命中多模态生成：multimodal(abstract)；分类 cs.AI

Comments 15 pages, 14 figures, in submission

2211.12845 2023-11-10 eess.IV cs.CV 57%

Super-resolution Reconstruction of Single Image for Latent features

Xin Wang, Jing-Ke Yan, Jing-Ye Cai, Jian-Hua Deng, Qin Qin, Yao Cheng

专题命中多模态生成：multimodal(abstract)；分类 cs.CV

Journal ref Computational Visual Media,2023

2310.18840 2023-11-09 cs.CV 57%

Customizing 360-Degree Panoramas through Text-to-Image Diffusion Models

Hai Wang, Xiaoyu Xiang, Yuchen Fan, Jing-Hao Xue

专题命中多模态生成：image-text(abstract)；分类 cs.CV

Comments Accepted by WACV 2024, Project Page: https://littlewhitesea.github.io/stitchdiffusion.github.io/

2311.04199 2023-11-08 cs.IR cs.CL 57%

Exploring Recommendation Capabilities of GPT-4V(ision): A Preliminary Case Study

Peilin Zhou, Meng Cao, You-Liang Huang, Qichen Ye, Peiyan Zhang, Junling Liu, Yueqi Xie, Yining Hua, Jaeboum Kim

专题命中多模态生成：multimodal(abstract)；分类 cs.CL

Comments In Progress

2311.03074 2023-11-07 eess.IV cs.CV 57%

A Two-Stage Generative Model with CycleGAN and Joint Diffusion for MRI-based Brain Tumor Detection

Wenxin Wang, Zhuo-Xu Cui, Guanxun Cheng, Chentao Cao, Xi Xu, Ziwei Liu, Haifeng Wang, Yulong Qi, Dong Liang, Yanjie Zhu

专题命中多模态生成：multimodal(abstract)；分类 cs.CV

Comments 11 pages,9 figures,3 tables

2305.02541 2023-11-07 cs.CV cs.GT 57%

Catch Missing Details: Image Reconstruction with Frequency Augmented Variational Autoencoder

Xinmiao Lin, Yikang Li, Jenhao Hsiao, Chiuman Ho, Yu Kong

专题命中多模态生成：image-text(abstract)；分类 cs.CV

Comments Accepted by CVPR 2023, code available at https://github.com/oppo-us-research/FA-VAE

2311.00339 2023-11-02 cs.CV stat.ML 57%

Space Narrative: Generating Images and 3D Scenes of Chinese Garden from Text using Deep Learning

Jiaxi Shi1, Hao Hua1

专题命中多模态生成：image-text(abstract)；分类 cs.CV

Comments 8 pages, 5 figures, xArch symposium

2307.09036 2023-11-02 cs.AI cs.HC 57%

PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation

Yingchaojie Feng, Xingbo Wang, Kam Kwai Wong, Sijia Wang, Yuhong Lu, Minfeng Zhu, Baicheng Wang, Wei Chen

专题命中多模态生成：cross-modal(abstract)；分类 cs.AI

Comments Accepted full paper for IEEE VIS 2023

2305.16381 2023-11-02 cs.LG cs.CV 57%

DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models

Ying Fan, Olivia Watkins, Yuqing Du, Hao Liu, Moonkyung Ryu, Craig Boutilier, Pieter Abbeel, Mohammad Ghavamzadeh, Kangwook Lee, Kimin Lee

专题命中多模态生成：image-text(abstract)；分类 cs.CV

Comments NeurIPS 2023

2305.10855 2023-10-31 cs.CV 57%

TextDiffuser: Diffusion Models as Text Painters

Jingye Chen, Yupan Huang, Tengchao Lv, Lei Cui, Qifeng Chen, Furu Wei

专题命中多模态生成：image-text(abstract)；分类 cs.CV

Comments NeurIPS 2023

2303.04053 2023-10-27 cs.CL 57%

Describe me an Aucklet: Generating Grounded Perceptual Category Descriptions

Bill Noble, Nikolai Ilinykh

专题命中多模态生成：multi-modal(abstract)；分类 cs.CL

Comments To appear in Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP, Main)

2310.15587 2023-10-25 cs.CL 57%

ScanDL: A Diffusion Model for Generating Synthetic Scanpaths on Texts

Lena S. Bolliger, David R. Reich, Patrick Haller, Deborah N. Jakobi, Paul Prasse, Lena A. Jäger

专题命中多模态生成：multi-modal(abstract)；分类 cs.CL

Comments EMNLP 2023

2310.15144 2023-10-24 cs.CV 57%

DEsignBench: Exploring and Benchmarking DALL-E 3 for Imagining Visual Design

Kevin Lin, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Lijuan Wang

专题命中多模态生成：image-text(abstract)；分类 cs.CV

Comments Project page at https://design-bench.github.io/

2310.14570 2023-10-24 cs.CV cs.RO 57%

DICE: Diverse Diffusion Model with Scoring for Trajectory Prediction

Younwoo Choi, Ray Coden Mercurius, Soheil Mohamad Alizadeh Shabestary, Amir Rasouli

专题命中多模态生成：multimodal(abstract)；分类 cs.CV

2305.14312 2023-10-23 cs.CV 57%

Text-guided 3D Human Generation from 2D Collections

Tsu-Jui Fu, Wenhan Xiong, Yixin Nie, Jingyu Liu, Barlas Oğuz, William Yang Wang

专题命中多模态生成：cross-modal(abstract)；分类 cs.CV

Comments EMNLP'23 (Findings) ; Project website: https://text-3dh.github.io/

2310.10651 2023-10-17 cs.CV cs.GR 57%

HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending

Tianyi Wei, Dongdong Chen, Wenbo Zhou, Jing Liao, Weiming Zhang, Gang Hua, Nenghai Yu

专题命中多模态生成：cross-modal(abstract)；分类 cs.CV

Comments ICCV 2023, code is available at https://github.com/wty-ustc/HairCLIPv2

2303.10137 2023-10-17 cs.CV cs.CR cs.LG 57%

A Recipe for Watermarking Diffusion Models

Yunqing Zhao, Tianyu Pang, Chao Du, Xiao Yang, Ngai-Man Cheung, Min Lin

专题命中多模态生成：multimodal(abstract)；分类 cs.CV

2309.15505 2023-10-13 cs.CV cs.LG 57%

Finite Scalar Quantization: VQ-VAE Made Simple

Fabian Mentzer, David Minnen, Eirikur Agustsson, Michael Tschannen

专题命中多模态生成：multimodal(abstract)；分类 cs.CV

Comments Code: https://github.com/google-research/google-research/tree/master/fsq

2305.18459 2023-10-11 cs.LG cs.AI 57%

Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning

Haoran He, Chenjia Bai, Kang Xu, Zhuoran Yang, Weinan Zhang, Dong Wang, Bin Zhao, Xuelong Li

专题命中多模态生成：multimodal(abstract)；分类 cs.AI

Comments Accepted by NeurIPS 2023. 22 pages

2304.08072 2023-10-11 eess.IV cs.CV cs.LG 57%

Two-stage MR Image Segmentation Method for Brain Tumors based on Attention Mechanism

Li Zhu, Jiawei Jiang, Lin Lu, Jin Li

专题命中多模态生成：multimodal(abstract)；分类 cs.CV

Comments Some contributing authors are not signed

2310.05410 2023-10-10 cs.AI 57%

Causal Reasoning through Two Layers of Cognition for Improving Generalization in Visual Question Answering

Trang Nguyen, Naoaki Okazaki

专题命中多模态生成：multimodal(abstract)；分类 cs.AI

2310.04929 2023-10-10 cs.CV cs.LG stat.ML 57%

DISCOVER: Making Vision Networks Interpretable via Competition and Dissection

Konstantinos P. Panousis, Sotirios Chatzis

专题命中多模态生成：multimodal(abstract)；分类 cs.CV

Comments Accepted @ NeuIPS 2023

2310.03218 2023-10-06 cs.LG cs.AI stat.ML 57%

Learning Energy-Based Prior Model with Diffusion-Amortized MCMC

Peiyu Yu, Yaxuan Zhu, Sirui Xie, Xiaojian Ma, Ruiqi Gao, Song-Chun Zhu, Ying Nian Wu

专题命中多模态生成：multi-modal(abstract)；分类 cs.AI

Comments NeurIPS 2023

1. 多模态生成 4965 篇

Unsupervised Anomaly Detection using Aggregated Normative Diffusion

FaceDNeRF: Semantics-Driven Face Reconstruction, Prompt Editing and Relighting with Diffusion Models

AvatarStudio: High-fidelity and Animatable 3D Avatar Creation from Text

Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning

Enhanced Synthetic MRI Generation from CT Scans Using CycleGAN with Feature Extraction

GeoViT: A Versatile Vision Transformer Architecture for Geospatial Image Analysis

MaGIC: Multi-modality Guided Image Completion

AtomXR: Streamlined XR Prototyping with Natural Language and Immersive Physical Interaction

Super-resolution Reconstruction of Single Image for Latent features

Customizing 360-Degree Panoramas through Text-to-Image Diffusion Models

Exploring Recommendation Capabilities of GPT-4V(ision): A Preliminary Case Study

A Two-Stage Generative Model with CycleGAN and Joint Diffusion for MRI-based Brain Tumor Detection

Catch Missing Details: Image Reconstruction with Frequency Augmented Variational Autoencoder

Space Narrative: Generating Images and 3D Scenes of Chinese Garden from Text using Deep Learning

PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation

DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models

TextDiffuser: Diffusion Models as Text Painters

Describe me an Aucklet: Generating Grounded Perceptual Category Descriptions

ScanDL: A Diffusion Model for Generating Synthetic Scanpaths on Texts

DEsignBench: Exploring and Benchmarking DALL-E 3 for Imagining Visual Design

DICE: Diverse Diffusion Model with Scoring for Trajectory Prediction

Text-guided 3D Human Generation from 2D Collections

HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending

A Recipe for Watermarking Diffusion Models

Finite Scalar Quantization: VQ-VAE Made Simple

Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning

Two-stage MR Image Segmentation Method for Brain Tumors based on Attention Mechanism

Causal Reasoning through Two Layers of Cognition for Improving Generalization in Visual Question Answering

DISCOVER: Making Vision Networks Interpretable via Competition and Dissection

Learning Energy-Based Prior Model with Diffusion-Amortized MCMC