中文
相关论文

相关论文: MAST: Mask-Guided Attention Mass Allocation for Tr…

200 篇论文

Both geometry and texture are fundamental aspects of visual style. Existing style transfer methods, however, primarily focus on texture, almost entirely ignoring geometry. We propose deformable style transfer (DST), an optimization-based…

计算机视觉与模式识别 · 计算机科学 2020-07-21 Sunnie S. Y. Kim , Nicholas Kolkin , Jason Salavon , Gregory Shakhnarovich

Controllable 3D style transfer seeks to restyle a 3D asset so that its textures match a reference image while preserving the integrity and multi-view consistency. The prevalent methods either rely on direct reference style token injection…

计算机视觉与模式识别 · 计算机科学 2025-10-14 Yuteng Ye , Zheng Zhang , Qinchuan Zhang , Di Wang , Youjia Zhang , Wenxiao Zhang , Wei Yang , Yuan Liu

Neural style transfer (NST) can create impressive artworks by transferring reference style to content image. Current image-to-image NST methods are short of fine-grained controls, which are often demanded by artistic editing. To mitigate…

计算机视觉与模式识别 · 计算机科学 2022-03-28 Zheng Lin , Zhao Zhang , Kang-Rui Zhang , Bo Ren , Ming-Ming Cheng

Recent neural style transfer frameworks have obtained astonishing visual quality and flexibility in Single-style Transfer (SST), but little attention has been paid to Multi-style Transfer (MST) which refers to simultaneously transferring…

计算机视觉与模式识别 · 计算机科学 2019-10-30 Zixuan Huang , Jinghuai Zhang , Jing Liao

Recent years have witnessed significant advancements in text-guided style transfer, primarily attributed to innovations in diffusion models. These models excel in conditional guidance, utilizing text or images to direct the sampling…

计算机视觉与模式识别 · 计算机科学 2025-04-18 Nisha Huang , Kaer Huang , Yifan Pu , Jiangshan Wang , Jie Guo , Yiqiang Yan , Xiu Li , Tong-Yee Lee

Representation learning aims to discover individual salient features of a domain in a compact and descriptive form that strongly identifies the unique characteristics of a given sample respective to its domain. Existing works in visual…

计算机视觉与模式识别 · 计算机科学 2023-08-21 Dan Ruta , Gemma Canet Tarres , Alexander Black , Andrew Gilbert , John Collomosse

Recent diffusion-based generators can produce high-quality images from textual prompts. However, they often disregard textual instructions that specify the spatial layout of the composition. We propose a simple approach that achieves robust…

计算机视觉与模式识别 · 计算机科学 2023-11-30 Minghao Chen , Iro Laina , Andrea Vedaldi

We introduce precise object silhouette as a new form of user control in text-to-image diffusion models, which we dub Shape-Guided Diffusion. Our training-free method uses an Inside-Outside Attention mechanism during the inversion and…

计算机视觉与模式识别 · 计算机科学 2024-04-02 Dong Huk Park , Grace Luo , Clayton Toste , Samaneh Azadi , Xihui Liu , Maka Karalashvili , Anna Rohrbach , Trevor Darrell

Recent diffusion-based image editing approaches have exhibited impressive editing capabilities in images with simple compositions. However, localized editing in complex scenarios has not been well-studied in the literature, despite its…

计算机视觉与模式识别 · 计算机科学 2023-12-22 Qi Mao , Lan Chen , Yuchao Gu , Zhen Fang , Mike Zheng Shou

Large language models have revolutionized AI applications, yet their high computational and memory demands hinder their widespread deployment. Existing compression techniques focus on intra-block optimizations (e.g., low-rank approximation…

计算与语言 · 计算机科学 2026-02-23 Magauiya Zhussip , Dmitriy Shopkhoev , Ammar Ali , Stamatios Lefkimmiatis

Large-scale diffusion models have achieved state-of-the-art results on text-to-image synthesis (T2I) tasks. Despite their ability to generate high-quality yet creative images, we observe that attribution-binding and compositional…

计算机视觉与模式识别 · 计算机科学 2023-03-02 Weixi Feng , Xuehai He , Tsu-Jui Fu , Varun Jampani , Arjun Akula , Pradyumna Narayana , Sugato Basu , Xin Eric Wang , William Yang Wang

Style transfer has attracted a lot of attentions, as it can change a given image into one with splendid artistic styles while preserving the image structure. However, conventional approaches easily lose image details and tend to produce…

计算机视觉与模式识别 · 计算机科学 2021-11-09 Suhyeon Ha , Guisik Kim , Junseok Kwon

Artistic style transfer aims to repaint the content image with the learned artistic style. Existing artistic style transfer methods can be divided into two categories: small model-based approaches and pre-trained large-scale model-based…

计算机视觉与模式识别 · 计算机科学 2023-12-12 Zhanjie Zhang , Quanwei Zhang , Guangyuan Li , Wei Xing , Lei Zhao , Jiakai Sun , Zehua Lan , Junsheng Luan , Yiling Huang , Huaizhong Lin

This paper presents MAST, a new model for Multimodal Abstractive Text Summarization that utilizes information from all three modalities -- text, audio and video -- in a multimodal video. Prior work on multimodal abstractive text…

计算与语言 · 计算机科学 2020-10-19 Aman Khullar , Udit Arora

Image editing approaches with diffusion models have been rapidly developed, yet their applicability are subject to requirements such as specific editing types (e.g., foreground or background object editing, style transfer), multiple…

计算机视觉与模式识别 · 计算机科学 2023-12-12 Yuming Qiao , Fanyi Wang , Jingwen Su , Yanhao Zhang , Yunjie Yu , Siyu Wu , Guo-Jun Qi

Text-to-image generation models have revolutionized content creation, but diffusion-based vision-language models still face challenges in precisely controlling the shape, appearance, and positional placement of objects in generated images…

计算机视觉与模式识别 · 计算机科学 2024-12-19 Shan Yang

Tuning-free diffusion-based models have demonstrated significant potential in the realm of image personalization and customization. However, despite this notable progress, current models continue to grapple with several complex challenges…

计算机视觉与模式识别 · 计算机科学 2024-04-08 Haofan Wang , Matteo Spinelli , Qixun Wang , Xu Bai , Zekui Qin , Anthony Chen

Attention-based arbitrary style transfer methods have gained significant attention recently due to their impressive ability to synthesize style details. However, the point-wise matching within the attention mechanism may overly focus on…

计算机视觉与模式识别 · 计算机科学 2025-02-10 Shuhao Zhang , Hui Kang , Yang Liu , Fang Mei , Hongjuan Li

Object-centric learning aims to decompose an input image into a set of meaningful object files (slots). These latent object representations enable a variety of downstream tasks. Yet, object-centric learning struggles on real-world datasets,…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Krishnakant Singh , Simone Schaub-Meyer , Stefan Roth

Extracting geometry features from photographic images independently of surface texture and transferring them onto different materials remains a complex challenge. In this study, we introduce Harmonizing Attention, a novel training-free…

计算机视觉与模式识别 · 计算机科学 2024-09-05 Eito Ikuta , Yohan Lee , Akihiro Iohara , Yu Saito , Toshiyuki Tanaka