图像生成 - arXivDaily 专题

2502.20235 2025-02-28 cs.CV 70%

Attention Distillation: A Unified Approach to Visual Characteristics Transfer

Yang Zhou, Xu Gao, Zichong Chen, Hui Huang

专题命中效率与蒸馏：image generation(abstract)；diffusion(abstract)；分类 cs.CV

Comments Accepted to CVPR 2025. Project page: https://github.com/xugao97/AttentionDistillation

2407.09896 2025-02-06 cs.CV eess.IV 70%

PSC: Posterior Sampling-Based Compression

Noam Elata, Tomer Michaeli, Michael Elad

专题命中效率与蒸馏：image generation(abstract)；diffusion(abstract)；分类 cs.CV

2405.09114 2025-01-03 cs.CV 70%

SOEDiff: Efficient Distillation for Small Object Editing

Yiming Wu, Qihe Pan, Zhen Zhao, Zicheng Wang, Sifan Long, Ronghua Liang

专题命中效率与蒸馏：diffusion(abstract)；inpainting(abstract)；分类 cs.CV

Comments preprint

2410.14919 2024-12-25 cs.CV cs.LG 70%

Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step

Mingyuan Zhou, Huangjie Zheng, Yi Gu, Zhendong Wang, Hai Huang

专题命中效率与蒸馏：image generation(abstract)；diffusion(abstract)；分类 cs.CV

Comments 10 pages (main text), 34 figures, and 10 tables

2412.12594 2024-12-18 cs.CV 70%

A Simple and Efficient Baseline for Zero-Shot Generative Classification

Zipeng Qi, Buhua Liu, Shiyan Zhang, Bao Li, Zhiqiang Xu, Haoyi Xiong, Zeke Xie

专题命中效率与蒸馏：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

2305.17235 2024-12-04 cs.CV cs.AI cs.LG 70%

COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models

Jinqi Xiao, Miao Yin, Yu Gong, Xiao Zang, Jian Ren, Bo Yuan

专题命中效率与蒸馏：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments ICML 2023 Poster

Journal ref Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38125-38136, 2023

2411.17178 2024-11-27 cs.CV 70%

LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization

Rui Xie, Tianchen Zhao, Zhihang Yuan, Rui Wan, Wenxi Gao, Zhenhua Zhu, Xuefei Ning, Yu Wang

专题命中效率与蒸馏：image generation(abstract)；diffusion(abstract)；分类 cs.CV

2411.04967 2024-11-08 cs.CV cs.LG 70%

AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation

Anil Kag, Huseyin Coskun, Jierun Chen, Junli Cao, Willi Menapace, Aliaksandr Siarohin, Sergey Tulyakov, Jian Ren

专题命中效率与蒸馏：image generation(abstract)；text-to-image(abstract)；分类 cs.CV

Comments NeurIPS 2024. Project Page: https://snap-research.github.io/snap_image/

2411.00605 2024-11-04 eess.IV cs.CV cs.LG 70%

pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization

Matthew C. Bendel, Rizwan Ahmad, Philip Schniter

专题命中效率与蒸馏：diffusion(abstract)；inpainting(abstract)；分类 cs.CV

Comments To appear at NeurIPS 2024

2410.16418 2024-10-28 cs.CV 70%

AttentionPainter: An Efficient and Adaptive Stroke Predictor for Scene Painting

Yizhe Tang, Yue Wang, Teng Hu, Ran Yi, Xin Tan, Lizhuang Ma, Yu-Kun Lai, Paul L. Rosin

专题命中效率与蒸馏：diffusion(abstract)；inpainting(abstract)；分类 cs.CV

2410.16892 2024-10-23 cs.CV 70%

VistaDream: Sampling multiview consistent images for single-view scene reconstruction

Haiping Wang, Yuan Liu, Ziwei Liu, Wenping Wang, Zhen Dong, Bisheng Yang

专题命中效率与蒸馏：diffusion(abstract)；inpainting(abstract)；分类 cs.CV

Comments Project Page: https://vistadream-project-page.github.io/

2410.13618 2024-10-18 cs.CV 70%

LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning

Yiming Shi, Jiwei Wei, Yujia Wu, Ran Ran, Chengwei Sun, Shiyuan He, Yang Yang

专题命中效率与蒸馏：image generation(abstract)；diffusion(abstract)；分类 cs.CV

Comments 13 pages, 7 figures

2410.10812 2024-10-15 cs.CV cs.AI cs.LG 70%

HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

Haotian Tang, Yecheng Wu, Shang Yang, Enze Xie, Junsong Chen, Junyu Chen, Zhuoyang Zhang, Han Cai, Yao Lu, Song Han

专题命中效率与蒸馏：image generation(abstract)；diffusion(abstract)；分类 cs.CV

Comments Demo: https://hart.mit.edu. The first two authors contributed equally to this work

2410.10511 2024-10-15 cs.CV 70%

Customize Your Visual Autoregressive Recipe with Set Autoregressive Modeling

Wenze Liu, Le Zhuo, Yi Xin, Sheng Xia, Peng Gao, Xiangyu Yue

专题命中效率与蒸馏：image generation(abstract)；text-to-image(abstract)；分类 cs.CV

Comments 19 pages, 17 figures, 8 tables, github repo: https://github.com/poppuppy/SAR

2405.20669 2024-10-10 cs.CV 70%

Hybrid Fourier Score Distillation for Efficient One Image to 3D Object Generation

Shuzhou Yang, Yu Wang, Haijie Li, Jiarui Meng, Yanmin Wu, Xiandong Meng, Jian Zhang

专题命中效率与蒸馏：image generation(abstract)；diffusion(abstract)；分类 cs.CV

2408.01291 2024-08-05 cs.CV 70%

TexGen: Text-Guided 3D Texture Generation with Multi-view Sampling and Resampling

Dong Huo, Zixin Guo, Xinxin Zuo, Zhihao Shi, Juwei Lu, Peng Dai, Songcen Xu, Li Cheng, Yee-Hong Yang

专题命中效率与蒸馏：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments European Conference on Computer Vision (ECCV) 2024

2407.21475 2024-08-01 cs.CV cs.AI 70%

Fine-gained Zero-shot Video Sampling

Dengsheng Chen, Jie Hu, Xiaoming Wei, Enhua Wu

专题命中效率与蒸馏：diffusion(abstract)；image synthesis(abstract)；分类 cs.CV

2407.06617 2024-07-24 cs.CV 70%

Mobius: A High Efficient Spatial-Temporal Parallel Training Paradigm for Text-to-Video Generation Task

Yiran Yang, Jinchao Zhang, Ying Deng, Jie Zhou

专题命中效率与蒸馏：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

2401.05293 2024-07-08 cs.CV 70%

Score Distillation Sampling with Learned Manifold Corrective

Thiemo Alldieck, Nikos Kolotouros, Cristian Sminchisescu

专题命中效率与蒸馏：diffusion(abstract)；image synthesis(abstract)；分类 cs.CV

2406.14964 2024-06-24 cs.CV 70%

VividDreamer: Towards High-Fidelity and Efficient Text-to-3D Generation

Zixuan Chen, Ruijie Su, Jiahao Zhu, Lingxiao Yang, Jian-Huang Lai, Xiaohua Xie

专题命中效率与蒸馏：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

2406.10019 2024-06-17 cs.LG cs.AI cs.CL cs.CV cs.NA math.NA 70%

Group and Shuffle: Efficient Structured Orthogonal Parametrization

Mikhail Gorbunov, Nikolay Yudin, Vera Soboleva, Aibek Alanov, Alexey Naumov, Maxim Rakhuba

专题命中效率与蒸馏：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

2406.10000 2024-06-17 cs.CV 70%

OrientDream: Streamlining Text-to-3D Generation with Explicit Orientation Control

Yuzhong Huang, Zhong Li, Zhang Chen, Zhiyuan Ren, Guosheng Lin, Fred Morstatter, Yi Xu

专题命中效率与蒸馏：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

2406.07548 2024-06-12 cs.CV cs.IT cs.LG eess.IV math.IT 70%

Image and Video Tokenization with Binary Spherical Quantization

Yue Zhao, Yuanjun Xiong, Philipp Krähenbühl

专题命中效率与蒸馏：diffusion(abstract)；image synthesis(abstract)；分类 cs.CV

Comments Tech report

2305.08252 2024-06-11 cs.CV cs.AI 70%

Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunity

Raman Dutt, Linus Ericsson, Pedro Sanchez, Sotirios A. Tsaftaris, Timothy Hospedales

专题命中效率与蒸馏：image generation(abstract)；text-to-image(abstract)；分类 cs.CV

Comments Accepted as Oral Presentation at MIDL 2024

2311.17984 2024-05-28 cs.CV 70%

4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling

Sherwin Bahmani, Ivan Skorokhodov, Victor Rong, Gordon Wetzstein, Leonidas Guibas, Peter Wonka, Sergey Tulyakov, Jeong Joon Park, Andrea Tagliasacchi, David B. Lindell

专题命中效率与蒸馏：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments CVPR 2024; Project page: https://sherwinbahmani.github.io/4dfy

2311.06243 2024-04-30 cs.LG cs.AI cs.CL cs.CV 70%

Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization

Weiyang Liu, Zeju Qiu, Yao Feng, Yuliang Xiu, Yuxuan Xue, Longhui Yu, Haiwen Feng, Zhen Liu, Juyeon Heo, Songyou Peng, Yandong Wen, Michael J. Black, Adrian Weller, Bernhard Schölkopf

专题命中效率与蒸馏：text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments ICLR 2024 (v2: 34 pages, 19 figures)

2402.19159 2024-04-16 cs.CV 70%

Trajectory Consistency Distillation: Improved Latent Consistency Distillation by Semi-Linear Consistency Function with Trajectory Mapping

Jianbin Zheng, Minghui Hu, Zhongyi Fan, Chaoyue Wang, Changxing Ding, Dacheng Tao, Tat-Jen Cham

专题命中效率与蒸馏：text-to-image(abstract)；image synthesis(abstract)；分类 cs.CV

Comments Project Page: https://mhh0318.github.io/tcd

2404.05979 2024-04-10 cs.CV 70%

StoryImager: A Unified and Efficient Framework for Coherent Story Visualization and Completion

Ming Tao, Bing-Kun Bao, Hao Tang, Yaowei Wang, Changsheng Xu

专题命中效率与蒸馏：image generation(abstract)；text-to-image(abstract)；分类 cs.CV

Comments 17 pages

2311.13831 2024-04-03 cs.CV 70%

Posterior Distillation Sampling

Juil Koo, Chanho Park, Minhyuk Sung

专题命中效率与蒸馏：diffusion(abstract)；image editing(abstract)；分类 cs.CV

Comments Project page: https://posterior-distillation-sampling.github.io/

2404.00633 2024-04-02 cs.CV 70%

IPT-V2: Efficient Image Processing Transformer using Hierarchical Attentions

Zhijun Tu, Kunpeng Du, Hanting Chen, Hailing Wang, Wei Li, Jie Hu, Yunhe Wang

专题命中效率与蒸馏：image generation(abstract)；diffusion(abstract)；分类 cs.CV

1. 效率与蒸馏 2537 篇

Attention Distillation: A Unified Approach to Visual Characteristics Transfer

PSC: Posterior Sampling-Based Compression

SOEDiff: Efficient Distillation for Small Object Editing

Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step

A Simple and Efficient Baseline for Zero-Shot Generative Classification

COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models

LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization

AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation

pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization

AttentionPainter: An Efficient and Adaptive Stroke Predictor for Scene Painting

VistaDream: Sampling multiview consistent images for single-view scene reconstruction

LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning

HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

Customize Your Visual Autoregressive Recipe with Set Autoregressive Modeling

Hybrid Fourier Score Distillation for Efficient One Image to 3D Object Generation

TexGen: Text-Guided 3D Texture Generation with Multi-view Sampling and Resampling

Fine-gained Zero-shot Video Sampling

Mobius: A High Efficient Spatial-Temporal Parallel Training Paradigm for Text-to-Video Generation Task

Score Distillation Sampling with Learned Manifold Corrective

VividDreamer: Towards High-Fidelity and Efficient Text-to-3D Generation

Group and Shuffle: Efficient Structured Orthogonal Parametrization

OrientDream: Streamlining Text-to-3D Generation with Explicit Orientation Control

Image and Video Tokenization with Binary Spherical Quantization

Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunity

4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling

Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization

Trajectory Consistency Distillation: Improved Latent Consistency Distillation by Semi-Linear Consistency Function with Trajectory Mapping

StoryImager: A Unified and Efficient Framework for Coherent Story Visualization and Completion

Posterior Distillation Sampling

IPT-V2: Efficient Image Processing Transformer using Hierarchical Attentions